© 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. 8438
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code syntax

    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¯įà®Ł
    -0.06
    .au
    -0.06
    ISTI
    -0.06
    anford
    -0.06
    usak
    -0.06
    èĢģåħļåijĺ
    -0.06
    æĽ´æ³¨éĩį
    -0.06
     DISCLAIMER
    -0.06
    ÑĸлÑĮ
    -0.06
    è£ģ
    -0.06
    POSITIVE LOGITS
     domesti
    0.07
    "]/
    0.07
    èĥ½æīĵ
    0.07
    ×ĺ×Ķ
    0.07
    RAIN
    0.07
    ocket
    0.06
    åĨįä¸ī
    0.06
     âĺħâĺħâĺħâĺħ
    0.06
    mdir
    0.06
    -relative
    0.06
    Activations Density 0.033%

    No Known Activations