© 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. 15614
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns

    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
     its
    -0.07
    _client
    -0.07
    缩
    -0.07
    utu
    -0.06
    çĽĺ
    -0.06
    Client
    -0.06
     compos
    -0.06
    веÑĢÑĪенÑģÑĤво
    -0.06
    кла
    -0.06
    åIJ¸
    -0.06
    POSITIVE LOGITS
    ç½ijæł¡
    0.08
    ={({
    0.07
    onal
    0.07
    \xa
    0.07
    ORED
    0.07
    _hdl
    0.07
    isper
    0.07
    ืà¸Ļ
    0.07
    ä»Ļåīij
    0.07
    åľ¨å¿ħ
    0.07
    Activations Density 0.002%

    No Known Activations