© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 72152
    Prev
    Next
    INDEX
    Explanations

    pulmonary embolism

    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
    Negative Logits
     Serial
    -0.08
     Hurt
    -0.07
    Inactive
    -0.07
     LINK
    -0.07
    Focus
    -0.07
    -powered
    -0.07
     العلاقة
    -0.07
     Pool
    -0.07
    heap
    -0.07
    damn
    -0.07
    POSITIVE LOGITS
    取得以及
    0.07
     notably
    0.07
    蜚
    0.07
    Other
    0.07
     decidedly
    0.06
    ública
    0.06
    所提供
    0.06
    óg
    0.06
    充分体现
    0.06
    个工作
    0.06
    Activations Density 0.003%

    No Known Activations