© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46420
    Prev
    Next
    INDEX
    Explanations

    State University

    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
    å¤©åľ°
    -0.07
    صÙĦ
    -0.07
    éļıç¼ĺ
    -0.07
    æľ¨å¤´
    -0.07
     unserialize
    -0.07
    vh
    -0.07
    èµĭ
    -0.07
    æľ¬èº«å°±æĺ¯
    -0.07
     alone
    -0.07
    .hasOwnProperty
    -0.07
    POSITIVE LOGITS
     Baik
    0.07
    core
    0.07
     Form
    0.07
    -sn
    0.06
    ernal
    0.06
    å®Įæķ´çīĪ
    0.06
    å·¥åħ·çļĦ
    0.06
    spark
    0.06
    tool
    0.06
    çĽijçĿ£åĴĮ
    0.06
    Activations Density 0.016%

    No Known Activations