© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45540
    Prev
    Next
    INDEX
    Explanations

    at

    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
     hakkı
    -0.08
     ויש
    -0.07
     бог
    -0.07
     Dip
    -0.07
    .setImageBitmap
    -0.07
     vigorously
    -0.07
    魔鬼
    -0.07
    油腻
    -0.07
     Sid
    -0.07
     ($("#
    -0.07
    POSITIVE LOGITS
    )
↵
↵
↵
    0.07
    分离
    0.07
    т
    0.07
    莎
    0.07
     successes
    0.07
    'un
    0.07
    */↵
    0.07
    SL
    0.07
    だったら
    0.07
    ứt
    0.06
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.