© 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. 42950
    Prev
    Next
    INDEX
    Explanations

    week’s episode

    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
    /edit
    -0.06
    ade
    -0.06
    se
    -0.06
    宣è¨Ģ
    -0.06
    Âł
    -0.06
    inds
    -0.06
    COM
    -0.06
    d
    -0.06
    ç¨ĢéĩĬ
    -0.06
    Pu
    -0.06
    POSITIVE LOGITS
    odos
    0.08
    ä¸Ģåĵģ
    0.08
    大éĢļ
    0.08
    borgen
    0.08
    _SCOPE
    0.08
    aira
    0.08
    emani
    0.08
    angani
    0.08
    æĿIJæĸĻåıĬ
    0.07
    alang
    0.07
    Activations Density 0.001%

    No Known Activations