© 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. 60139
    Prev
    Next
    INDEX
    Explanations

    Air Force

    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
    elv
    -0.08
    å¼Ģæĭĵè¿Ľåıĸ
    -0.08
    æįĮ
    -0.07
     abol
    -0.07
    æĬ½çŃĭ
    -0.07
    纲
    -0.07
    举åįĩ
    -0.07
    otime
    -0.07
    çīŁå°¼
    -0.07
    elij
    -0.07
    POSITIVE LOGITS
    ä¼ı
    0.08
     otherwise
    0.07
    imb
    0.06
    åħ·
    0.06
    _nbr
    0.06
    OrDefault
    0.06
    è°ħ
    0.06
     supposed
    0.06
    aray
    0.06
    າàºĻ
    0.06
    Activations Density 0.007%

    No Known Activations