© 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. 5849
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    时光
    -0.08
     Mist
    -0.07
     Taken
    -0.07
    之所
    -0.07
    鲜明
    -0.07
    rift
    -0.07
     tim
    -0.07
    plaintext
    -0.06
     recognize
    -0.06
    attention
    -0.06
    POSITIVE LOGITS
     RPG
    0.07
    (st
    0.07
    _set
    0.07
    🌑
    0.07
     shaders
    0.07
    .ctrl
    0.07
    .argv
    0.07
    (QStringLiteral
    0.07
     Pagination
    0.07
    扫黑
    0.07
    Activations Density 0.004%

    No Known Activations