© 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. 40176
    Prev
    Next
    INDEX
    Explanations

    chip and pin cards

    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
    uhi
    -0.09
    _rewrite
    -0.08
    olu
    -0.08
    ä¸įæ¯Ķ
    -0.08
    åľ¨æľ¬ç«Ļ
    -0.08
     misd
    -0.08
    Mahon
    -0.08
    _ASSUME
    -0.07
    kov
    -0.07
    azah
    -0.07
    POSITIVE LOGITS
    ä¸Ńä¹ĭ
    0.06
    Vo
    0.06
    oret
    0.06
    antly
    0.06
    å°½
    0.06
    nhard
    0.06
    ipo
    0.06
    åĬłæĭ¿å¤§
    0.06
    IDE
    0.06
    ipy
    0.05
    Activations Density 0.594%

    No Known Activations