© 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. 42854
    Prev
    Next
    INDEX
    Explanations

    spy club or forced command

    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
    igr
    -0.09
     -
    -0.07
    ä¸İç»´æĬ¤
    -0.06
    imo
    -0.06
    -</
    -0.06
    gmt
    -0.06
    æĽ´å¤ļ精彩
    -0.06
    èĢĮèµ°
    -0.06
    âĢij
    -0.06
    走好
    -0.06
    POSITIVE LOGITS
     **.**
    0.08
    _=
    0.08
     ([]
    0.08
    trup
    0.07
    otÄĻ
    0.07
     tev
    0.07
    å±ī
    0.07
    椿
    0.07
    iedad
    0.07
    raud
    0.07
    Activations Density 0.074%

    No Known Activations