© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    intent data, join, binding, derive, twists

    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
    à¸Ľà¸£
    -0.06
    Ù°
    -0.06
    ="__
    -0.06
    ç¢į
    -0.06
    beros
    -0.06
    ÑĩинÑĭ
    -0.06
    ummy
    -0.06
    üten
    -0.06
    èĥ¡æ¤Ĵç²ī
    -0.06
    åĶ¬
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.08
    opter
    0.08
    kening
    0.07
    usc
    0.07
    è¾ħ
    0.07
    çĮ
    0.07
    komst
    0.07
    Anything
    0.07
    é¾Ļæ½Ń
    0.07
     Especial
    0.07
    Activations Density 0.026%

    No Known Activations