© 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. 19013
    Prev
    Next
    INDEX
    Explanations

    computational chemistry and technical text

    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
    åĽ½æŃĮ
    -0.07
    Ñħло
    -0.07
    è·»
    -0.06
    绣ä¸Ģ管çIJĨ
    -0.06
    emean
    -0.06
    .Minimum
    -0.06
    åħ¥åı£
    -0.06
     Loot
    -0.06
    gid
    -0.06
    zuki
    -0.06
    POSITIVE LOGITS
    syl
    0.08
    ä¸īéĩį
    0.07
    åij±
    0.07
    éĢĥ亡
    0.07
    ĥĿ
    0.07
    WindowTitle
    0.07
     κÏĮÏĥ
    0.07
    OWER
    0.07
    åħ¨å¥Ĺ
    0.07
    à®¿à®Łà¯įà®Ł
    0.07
    Activations Density 0.012%

    No Known Activations