© 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. 51656
    Prev
    Next
    INDEX
    Explanations

    versions, similarity, mirror, data, tanker, copyright

    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
     Ñģквоз
    -0.07
    affle
    -0.07
    å¹ķ
    -0.07
    æľīåIJį
    -0.07
    macher
    -0.07
    ãĥĶãĤ½ãĥ¼ãĥī
    -0.07
    зина
    -0.07
    _NATIVE
    -0.07
    illon
    -0.07
    é«ĺé«ĺçļĦ
    -0.07
    POSITIVE LOGITS
    é¾Ł
    0.07
    æľ½
    0.07
    rak
    0.07
    çļĦäºĭä¸ļ
    0.06
    ä¸ĢåĽ¾
    0.06
    tyw
    0.06
     seit
    0.06
    çģ
    0.06
    ä¸įåĽŀ
    0.06
    drv
    0.06
    Activations Density 0.001%

    No Known Activations