© 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. 19-RESID-POST-AA
    11. 68917
    Prev
    Next
    INDEX
    Explanations

    computer code/API responses

    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
    等情况
    -0.07
    聲
    -0.07
    يش
    -0.07
    	xml
    -0.07
    theses
    -0.07
    的利益
    -0.07
    会造成
    -0.06
    juana
    -0.06
    ein
    -0.06
     conserve
    -0.06
    POSITIVE LOGITS
    :**
    0.08
     custom
    0.07
     Stout
    0.07
    wick
    0.07
     ****************************************
    0.07
    比如
    0.07
    案例
    0.07
     riv
    0.06
     Nike
    0.06
     RTL
    0.06
    Activations Density 0.014%

    No Known Activations