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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 69517
    Prev
    Next
    INDEX
    Explanations

    Music albums

    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
    aturity
    -0.07
     Quran
    -0.07
    辈
    -0.07
    临
    -0.07
     forb
    -0.06
     Voor
    -0.06
    iciary
    -0.06
     formulated
    -0.06
    浙
    -0.06
    採
    -0.06
    POSITIVE LOGITS
     aDecoder
    0.08
    Mos
    0.07
     "->
    0.07
    转变为
    0.07
     실제로
    0.07
     IDM
    0.07
    主题活动
    0.07
    AGES
    0.07
    关乎
    0.07
     UIS
    0.06
    Activations Density 0.056%

    No Known Activations