© 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. 1227
    Prev
    Next
    INDEX
    Explanations

    ":" followed by digits or specific words

    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
    ptom
    -0.07
     concor
    -0.07
     (--
    -0.07
     {[
    -0.07
    pm
    -0.07
    ãĥ¥ãĥ¼
    -0.07
    æĻļæĬ¥
    -0.07
    á»ĩu
    -0.07
    /pm
    -0.06
    mon
    -0.06
    POSITIVE LOGITS
    -files
    0.07
    aliz
    0.07
    apers
    0.07
    Ahead
    0.07
    ahead
    0.06
    erule
    0.06
    å°ģç¥ŀ
    0.06
    ads
    0.06
    anzi
    0.06
     ver
    0.06
    Activations Density 0.001%

    No Known Activations