© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115913
    Prev
    Next
    INDEX
    Explanations

    controversial topics

    np_max-act · gemini-2.0-flash

    harmful or policy-violating content, including hate speech, bigotry, sexual or extreme violence, and instructions to cause harm.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reward
    -0.07
     Fir
    -0.06
    став
    -0.06
    \Security
    -0.06
    Timeout
    -0.06
     Workout
    -0.06
    .extract
    -0.06
    就读
    -0.06
     complicated
    -0.06
    を受け
    -0.06
    POSITIVE LOGITS
    .branch
    0.07
     Fly
    0.07
     pcs
    0.07
    保修
    0.07
    (amount
    0.07
    packing
    0.07
    Singapore
    0.07
     Lista
    0.07
    QUENCY
    0.07
    .imag
    0.06
    Activations Density 1.080%

    No Known Activations