© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 129203
    Prev
    Next
    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    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
    ند
    -0.07
     divis
    -0.07
    웹
    -0.07
     Montgomery
    -0.07
     منها
    -0.07
     downs
    -0.07
    obe
    -0.07
    使者
    -0.06
     Usa
    -0.06
     соответ
    -0.06
    POSITIVE LOGITS
    ={}↵
    0.07
    	Q
    0.07
     sequelize
    0.07
    สาว
    0.07
     Virtual
    0.07
    .construct
    0.07
    .Head
    0.07
     Pro
    0.07
    ecure
    0.07
    _dialog
    0.07
    Activations Density 0.003%

    No Known Activations