© 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. 40661
    Prev
    Next
    INDEX
    Explanations

    vector space or partition

    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
    attel
    -0.08
    åĨīåĨī
    -0.07
    óre
    -0.07
    严å®Ī
    -0.06
    à¹Ģà¸ŀ
    -0.06
    ä¸įå°±
    -0.06
    ummy
    -0.06
    æĸĩåĵ²
    -0.06
     Ridley
    -0.06
    onos
    -0.06
    POSITIVE LOGITS
    æľĢéļ¾
    0.08
     notoriously
    0.08
    ffy
    0.08
    ipas
    0.07
    bidden
    0.07
    é¾ĻèĻİ
    0.07
    èĢ¶
    0.07
    asy
    0.07
    说ä¸į
    0.07
    åħ¨åĬĽä»¥èµ´
    0.06
    Activations Density 0.075%

    No Known Activations