© 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. 15297
    Prev
    Next
    INDEX
    Explanations

    class, file, or variable names

    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
    ëĵł
    -0.06
    æĸĹ
    -0.06
    azio
    -0.06
    à®Łà®¿à®¯
    -0.06
    STYPE
    -0.06
    夹
    -0.06
    ä¼Ļ
    -0.06
    åĶĶ
    -0.06
    ansch
    -0.06
     hashing
    -0.06
    POSITIVE LOGITS
    ÑħваÑĤ
    0.08
    affer
    0.07
    olygon
    0.07
    íĩ´
    0.07
    责任ç¼ĸè¾ij
    0.07
    Ľ
    0.07
    ulte
    0.07
    âĺĨâĺĨ
    0.07
    ãĤªãĥ¼ãĥ«
    0.07
    ponce
    0.07
    Activations Density 0.252%

    No Known Activations