© 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. 41150
    Prev
    Next
    INDEX
    Explanations

    compared to

    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
    gens
    -0.07
    appelle
    -0.07
    æıŃ示
    -0.07
    ç§ĭåįĥ
    -0.07
    enio
    -0.07
    ön
    -0.07
     Pellegr
    -0.07
    æĺ¾ç¤º
    -0.07
    laub
    -0.07
    apy
    -0.07
    POSITIVE LOGITS
    ag
    0.07
     function
    0.07
    çĪ±æ°ij
    0.07
    aft
    0.06
    大æĸ¹çļĦ
    0.06
    èĢģä¼´
    0.06
     Mol
    0.06
    afc
    0.06
    /export
    0.06
     ...
    0.06
    Activations Density 0.001%

    No Known Activations