© 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. 11-RESID-POST-AA
    11. 26145
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    转移
    -0.07
     clinging
    -0.07
    情緒
    -0.07
    selector
    -0.07
    做好
    -0.07
    意愿
    -0.07
    immutable
    -0.06
    .ep
    -0.06
     simulate
    -0.06
    CTION
    -0.06
    POSITIVE LOGITS
     ?>">
    0.07
    rad
    0.07
    رم
    0.07
    erie
    0.07
    _masks
    0.07
     hairy
    0.06
    Nhap
    0.06
     الكبرى
    0.06
     Bruno
    0.06
    ApiClient
    0.06
    Activations Density 0.194%

    No Known Activations