Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 87848
    Prev
    Next
    INDEX
    Explanations

    say import

    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
    משכ
    -0.07
    -duration
    -0.07
     />);↵
    -0.07
     ----------------------------------------------------------------
    -0.07
    ()];↵
    -0.07
    ۦ
    -0.07
     ContentValues
    -0.07
    orElse
    -0.07
     שמורות
    -0.07
     עצמ
    -0.07
    POSITIVE LOGITS
    -errors
    0.07
    姚
    0.07
    WM
    0.06
     disc
    0.06
    얽
    0.06
    te
    0.06
     Lake
    0.06
     Hall
    0.06
    	The
    0.06
     permanent
    0.06
    Activations Density 0.010%

    No Known Activations