© 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. 29007
    Prev
    Next
    INDEX
    Explanations

    output from

    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
    iger
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    éĢĬ
    -0.06
    çķ¦
    -0.06
    .localized
    -0.06
    ordinator
    -0.06
    ++,
    -0.06
     Ordn
    -0.06
    iems
    -0.06
    å®Ľ
    -0.06
    POSITIVE LOGITS
    .createFrom
    0.08
    ä¸İæĸ¹æ³ķ
    0.08
    orelease
    0.07
    erma
    0.07
    æīĵåĩºäºĨ
    0.07
    æĬ¢åħĪ
    0.07
    çĶĺå¿ĥ
    0.07
    æĢĿç»´èĥ½åĬĽ
    0.07
    -hide
    0.06
    :)
    0.06
    Activations Density 0.001%

    No Known Activations