© 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. 34044
    Prev
    Next
    INDEX
    Explanations

    . or ,

    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
    ltre
    -0.07
    éļıå¤Ħ
    -0.07
    ServiceProvider
    -0.07
     iepazÄ«Å¡anÄģs
    -0.07
    opsy
    -0.07
     Ùħرد
    -0.07
    ä¸ĢåĽ¢
    -0.07
    ethereum
    -0.07
    rets
    -0.07
    _SKIP
    -0.06
    POSITIVE LOGITS
    ä½Ĩ对äºİ
    0.07
    crest
    0.07
    è¿Ļå°±è¦ģæ±Ĥ
    0.07
    ounge
    0.07
    isco
    0.07
    ourd
    0.06
    èĬ±é¦Ļ
    0.06
    éĴĪ对
    0.06
    oot
    0.06
    å±ħå¤ļ
    0.06
    Activations Density 0.036%

    No Known Activations