© 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. 26437
    Prev
    Next
    INDEX
    Explanations

    separators and delimiters

    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
    coni
    -0.07
    第ä¸Ģ件äºĭ
    -0.07
    oice
    -0.06
    æĬijæĪĸ
    -0.06
    Chunk
    -0.06
    ibel
    -0.06
    åĬŁåĬ³
    -0.06
    åĵī
    -0.06
    illon
    -0.06
    வà¯ĩ
    -0.06
    POSITIVE LOGITS
    usz
    0.07
    å¾Ĵ
    0.07
    __[
    0.07
    aine
    0.07
    è¡·
    0.07
    abin
    0.07
    nheim
    0.06
    æľīåºıå¼Ģå±ķ
    0.06
    è¡¢
    0.06
    计ç®Ĺæĸ¹æ³ķ
    0.06
    Activations Density 0.007%

    No Known Activations