© 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. 39572
    Prev
    Next
    INDEX
    Explanations

    ac

    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
    非常
    -0.07
     JA
    -0.07
    .Direct
    -0.07
    inue
    -0.07
    /view
    -0.07
     행복
    -0.07
     unfit
    -0.07
     continuous
    -0.07
     Mood
    -0.07
    alk
    -0.06
    POSITIVE LOGITS
    短缺
    0.07
     Sonia
    0.07
    ريع
    0.07
     ليبي
    0.07
     Reagan
    0.07
    股权转让
    0.07
     Libertarian
    0.07
     hacked
    0.07
    逭
    0.07
     closeButton
    0.07
    Activations Density 0.001%

    No Known Activations