© 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. 75885
    Prev
    Next
    INDEX
    Explanations

    say "distribution"

    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
    (withDuration
    -0.07
     amusement
    -0.07
    -flash
    -0.07
    ilyn
    -0.07
    *dx
    -0.07
     cleanliness
    -0.07
    	Global
    -0.07
    Um
    -0.07
     dislikes
    -0.07
    xCE
    -0.07
    POSITIVE LOGITS
    оде
    0.07
     Waters
    0.07
    開
    0.07
     компания
    0.07
    от
    0.06
    -----↵↵
    0.06
    ⚣
    0.06
     "["
    0.06
    atk
    0.06
     referring
    0.06
    Activations Density 0.009%

    No Known Activations