© 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. 34682
    Prev
    Next
    INDEX
    Explanations

    compliance, panning, low, misconceptions, reputation, calming, season, payments, recalled, actors

    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
    å¾·éŁ³
    -0.09
    ciuti
    -0.09
    ä¸ĢçĽ´ä»¥
    -0.08
    æł©æł©
    -0.08
    renom
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    łĢ
    -0.08
    çĦ¶å¤§
    -0.08
    å¸Ĥä¸Ń级人æ°ijæ³ķéĻ¢
    -0.08
     onCancelled
    -0.08
    POSITIVE LOGITS
    æĪĸæĺ¯
    0.08
    æĪĸèĢħ
    0.07
    æĪĸèĢħæĺ¯
    0.07
    -
    0.07
    æĪĸèĢħæľī
    0.07
     (?)
    0.07
    (?)
    0.07
    (
    0.06
    ãĢģ
    0.06
    /
    0.06
    Activations Density 3.175%

    No Known Activations