© 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. 19-RESID-POST-AA
    6. 109360
    Prev
    Next
    INDEX
    Explanations

    Code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    殺
    -0.07
    .stopPropagation
    -0.07
    ava
    -0.07
     경우에는
    -0.07
    _CAPACITY
    -0.07
     champions
    -0.06
    //@
    -0.06
    パパ
    -0.06
    annies
    -0.06
     ese
    -0.06
    POSITIVE LOGITS
     ROOT
    0.07
    安徽
    0.07
     חברות
    0.07
     Stub
    0.07
    工序
    0.06
     TITLE
    0.06
    𝐊
    0.06
    IBUTES
    0.06
     irrit
    0.06
    }-${
    0.06
    Activations Density 0.112%

    No Known Activations