© 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. 26419
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    éĿ¢ç§¯çº¦
    -0.07
    landers
    -0.07
     RGBA
    -0.07
    à°¡à±į
    -0.07
    íģIJ
    -0.07
    isters
    -0.07
    OPTIONS
    -0.07
    <|box_end|>
    -0.07
    à¹ģสà¸Ļ
    -0.07
    Inflater
    -0.07
    POSITIVE LOGITS
    otre
    0.06
    InThe
    0.06
    _ARG
    0.06
    otr
    0.06
     assumed
    0.06
    贯穿
    0.06
    å¸ĥä»Ģ
    0.06
    enor
    0.06
    azzi
    0.06
    å¹³çŃī
    0.06
    Activations Density 0.081%

    No Known Activations