© 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. 41468
    Prev
    Next
    INDEX
    Explanations

    visual plots and data structures

    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
    ayani
    -0.08
    èĩ»
    -0.08
    usher
    -0.08
    çĴ¨
    -0.08
     penetrating
    -0.08
    è¿IJè¡ĮçļĦ
    -0.07
    üm
    -0.07
    ç©¿éĢı
    -0.07
    azines
    -0.07
    æĹłéĿŀ
    -0.07
    POSITIVE LOGITS
    oule
    0.08
    éķ¿åº¦
    0.07
    éķ¿åº¦ä¸º
    0.07
     proportional
    0.07
     Bugs
    0.07
     length
    0.07
     parallel
    0.06
    åłĨ积
    0.06
    åIJįåĪ©
    0.06
    OAD
    0.06
    Activations Density 0.003%

    No Known Activations