© 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. 61490
    Prev
    Next
    INDEX
    Explanations

    path

    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
    溶液
    -0.07
    loud
    -0.07
    تحد
    -0.07
     Wise
    -0.07
    不服
    -0.07
     Ud
    -0.06
    Guess
    -0.06
    عقد
    -0.06
    ⇝
    -0.06
     alph
    -0.06
    POSITIVE LOGITS
    _about
    0.07
    \Redirect
    0.07
    总经理
    0.07
    立项
    0.07
     kvinna
    0.07
    kaar
    0.07
    CHE
    0.07
    .partial
    0.07
     cemetery
    0.06
    celona
    0.06
    Activations Density 0.009%

    No Known Activations