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. 35927
    Prev
    Next
    INDEX
    Explanations

    Game of Life

    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
     Conflict
    -0.07
     confidential
    -0.06
     flew
    -0.06
    湖北省
    -0.06
    Ə
    -0.06
     Users
    -0.06
    ļ
    -0.06
    .Ui
    -0.06
    izations
    -0.06
     Characteristics
    -0.06
    POSITIVE LOGITS
    matching
    0.07
    融创
    0.07
    starter
    0.07
    ⛷
    0.07
     commerce
    0.07
    桴
    0.07
    roll
    0.07
    儦
    0.06
    eor
    0.06
    /help
    0.06
    Activations Density 0.012%

    No Known Activations