© 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. 13840
    Prev
    Next
    INDEX
    Explanations

    function, tests, shooter, perfectly, $

    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
    erge
    -0.07
    ocas
    -0.07
    åĬ©åĬĽ
    -0.07
    éľĨ
    -0.07
    crew
    -0.07
     anonym
    -0.07
    èĦ±æ¯Ľ
    -0.07
     ((((
    -0.07
     grund
    -0.06
    osi
    -0.06
    POSITIVE LOGITS
    eze
    0.07
    sob
    0.07
    راد
    0.07
    èĴIJ
    0.07
    allel
    0.06
     memben
    0.06
     justified
    0.06
    äºĭæĥħ
    0.06
    æ£Ģå¯Łéķ¿
    0.06
    æĿ¥ç¡®å®ļ
    0.06
    Activations Density 0.024%

    No Known Activations