Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7243
    Prev
    Next
    INDEX
    Explanations

    regulations

    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
    /documentation
    -0.06
    gee
    -0.06
     modern
    -0.06
     Mem
    -0.06
     Smooth
    -0.06
    _Search
    -0.06
    Identification
    -0.06
    western
    -0.06
     Psychological
    -0.06
     James
    -0.06
    POSITIVE LOGITS
     salari
    0.08
    を目指
    0.08
    坦言
    0.08
    队员们
    0.07
    얕
    0.07
    .RowCount
    0.07
    堪称
    0.07
    عائل
    0.07
    츰
    0.07
    ₠
    0.07
    Activations Density 0.050%

    No Known Activations