© 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. 64678
    Prev
    Next
    INDEX
    Explanations

    Based on, According to, What with

    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
    è¿ĺæľī个
    -0.08
    isons
    -0.07
    indle
    -0.07
     rév
    -0.07
    ÃŃos
    -0.07
    iertos
    -0.06
    leden
    -0.06
    łĢ
    -0.06
     '\''
    -0.06
    iect
    -0.06
    POSITIVE LOGITS
    ush
    0.08
    éŀŃ
    0.07
    enberg
    0.07
    acar
    0.07
     Fleisch
    0.07
    omi
    0.07
    ou
    0.07
    å·¢
    0.07
    uš
    0.06
    inz
    0.06
    Activations Density 0.053%

    No Known Activations