© 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. 20173
    Prev
    Next
    INDEX
    Explanations

    Servlet, DO, alb, Obj, .r

    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
    Ñĩали
    -0.07
    arem
    -0.06
    ãģĿãģ®ä»ĸãģ®
    -0.06
    chestra
    -0.06
    ĥģ
    -0.06
     preferred
    -0.06
     |/
    -0.06
    èľĪ
    -0.06
    åĽŀåİ»åIJ§
    -0.06
    EndPoint
    -0.06
    POSITIVE LOGITS
    ksom
    0.08
    uca
    0.08
    elage
    0.08
    .proc
    0.07
    anza
    0.07
    LEAN
    0.07
    éĩij马
    0.07
    rir
    0.07
    OX
    0.07
     $($
    0.07
    Activations Density 0.058%

    No Known Activations