© 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. 19219
    Prev
    Next
    INDEX
    Explanations

    clicked, precondition, advances, graves, nurses, enemies, wrestler

    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
    çİĩåħĪ
    -0.07
    odon
    -0.07
    é¼İ
    -0.06
    çļĦä¸Ń
    -0.06
    .ro
    -0.06
    çħİ
    -0.06
    ç»ħ
    -0.06
    è¹ĭ
    -0.06
    åIJĦæĹı
    -0.06
     épouse
    -0.06
    POSITIVE LOGITS
     traditionally
    0.09
     ordinarily
    0.08
    trad
    0.08
    ldr
    0.08
     equivalent
    0.08
     equivalente
    0.08
     normally
    0.08
    lys
    0.07
     Equivalent
    0.07
     Derived
    0.07
    Activations Density 0.300%

    No Known Activations