© 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. 60313
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending in O, C, D, F

    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
    æľīä½Ļ
    -0.07
    æľīæīĢ
    -0.07
    itar
    -0.07
    æ²½
    -0.06
    徨
    -0.06
    åĴĨ
    -0.06
    ibar
    -0.06
     Hels
    -0.06
    姿
    -0.06
    odus
    -0.06
    POSITIVE LOGITS
    Func
    0.07
    adou
    0.07
    endon
    0.06
     tutel
    0.06
    .tom
    0.06
    çĪ±çļĦ人
    0.06
    érant
    0.06
     tempora
    0.06
     seng
    0.06
     richiam
    0.06
    Activations Density 0.034%

    No Known Activations