© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12225
    Prev
    Next
    INDEX
    Explanations

    words that evoke fear or disgust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    满èħĶ
    -0.09
    ptype
    -0.08
    atering
    -0.08
    errs
    -0.08
    å¥½å¥½åľ°
    -0.08
    ättning
    -0.08
    çĥŃéŨæIJľç´¢
    -0.08
    unno
    -0.08
    porté
    -0.08
    istus
    -0.08
    POSITIVE LOGITS
    ly
    0.14
    -looking
    0.12
    ness
    0.11
     ×ij×Ļ×ķתר
    0.11
    zze
    0.10
    erweise
    0.10
    LY
    0.09
    lier
    0.08
     ÙĦÙĦغاÙĬØ©
    0.08
    èĩ³æŀģ
    0.08
    Activations Density 0.350%

    No Known Activations