© 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. 15238
    Prev
    Next
    INDEX
    Explanations

    starting from rest or zero

    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
    invert
    -0.08
    ë¡Ģ
    -0.08
     dÃło
    -0.07
    åĽŀ车
    -0.07
     invert
    -0.07
    assung
    -0.07
    баÑĢов
    -0.07
    åĽŀäºĨ
    -0.07
     "\\"
    -0.07
     arity
    -0.07
    POSITIVE LOGITS
    ianya
    0.09
    å§ĭ
    0.07
    ish
    0.07
    éĿĻæŃ¢
    0.07
    arov
    0.07
    ä¹ĸä¹ĸ
    0.06
    æ²īéĩįçļĦ
    0.06
     gravi
    0.06
    æħ¢æħ¢åľ°
    0.06
    agno
    0.06
    Activations Density 0.004%

    No Known Activations