© 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. 11865
    Prev
    Next
    INDEX
    Explanations

    Please

    np_max-act · gemini-2.0-flash

    dialogue where someone is in distress and resisting, marked by crying, screaming, and pleading for mercy or for something to stop.

    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
    高地
    -0.07
     Communication
    -0.07
    slave
    -0.07
     emulate
    -0.07
     Bridge
    -0.07
    渥
    -0.07
     remedy
    -0.07
    upon
    -0.06
    Liverpool
    -0.06
     modificar
    -0.06
    POSITIVE LOGITS
     handmade
    0.08
     dicks
    0.07
    .EX
    0.07
     geb
    0.07
    .GetInt
    0.06
     책
    0.06
    ưu
    0.06
    庭审
    0.06
    NYSE
    0.06
    ABLE
    0.06
    Activations Density 0.088%

    No Known Activations