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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 81708
    Prev
    Next
    INDEX
    Explanations

    nested

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ende
    -0.08
    änger
    -0.08
    .Port
    -0.07
    >(_
    -0.07
     ef
    -0.07
    lius
    -0.07
     rationale
    -0.07
    atetime
    -0.07
    leground
    -0.07
    和发展
    -0.07
    POSITIVE LOGITS
     disappointed
    0.07
    她们
    0.07
    .demo
    0.07
    網站
    0.07
     البحث
    0.07
    奖项
    0.07
    蹋
    0.07
     "~/
    0.07
     котором
    0.06
    אתר
    0.06
    Activations Density 0.005%

    No Known Activations