© 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. 23582
    Prev
    Next
    INDEX
    Explanations

    patent citation numbers

    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
    好ãģįãģª
    -0.07
    åĽĽ
    -0.07
    orsa
    -0.06
    ISTORY
    -0.06
    çķ¥
    -0.06
    ики
    -0.06
    older
    -0.06
     Tet
    -0.06
    å°¤
    -0.06
    ymar
    -0.06
    POSITIVE LOGITS
    zil
    0.07
     Baghd
    0.07
    rano
    0.07
    /vnd
    0.07
    utin
    0.07
    çł¥
    0.07
    å¤ļåѦç§ij
    0.07
     Maak
    0.07
    ç»ıå®¡æŁ¥
    0.07
     Christ
    0.07
    Activations Density 0.001%

    No Known Activations