© 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. 90081
    Prev
    Next
    INDEX
    Explanations

    sept

    np_max-act · gemini-2.0-flash
    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
     envi
    -0.07
    vine
    -0.07
     sails
    -0.06
     ciudad
    -0.06
    .primary
    -0.06
    宽阔
    -0.06
    :Register
    -0.06
    蜇
    -0.06
    焙
    -0.06
    一架
    -0.06
    POSITIVE LOGITS
    戆
    0.07
     regarding
    0.07
    	URL
    0.06
    .Local
    0.06
    そこで
    0.06
    很多人都
    0.06
    [M
    0.06
    /../
    0.06
    史上
    0.06
    感染
    0.06
    Activations Density 0.005%

    No Known Activations