© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    tissue growth and risk

    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
    outs
    -0.09
     outs
    -0.08
    西æĸ¯
    -0.08
    awang
    -0.08
    outers
    -0.08
    soles
    -0.07
    ä¸ĭæ°´
    -0.07
    Å¡ek
    -0.07
    uteurs
    -0.07
     *.*
    -0.07
    POSITIVE LOGITS
    unused
    0.07
    çĶ¨çļĦ
    0.07
    _dummy
    0.07
    -inspired
    0.07
    _detect
    0.07
    è±
    0.06
    _unused
    0.06
    fal
    0.06
    æĪIJ人
    0.06
     Jad
    0.06
    Activations Density 0.459%

    No Known Activations