© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    scales and times

    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
    羡
    -0.07
    çģ¿
    -0.06
     Completely
    -0.06
    çļĦåħ¨éĥ¨
    -0.06
     exactly
    -0.06
    posa
    -0.06
    nex
    -0.06
     flawless
    -0.06
     graduated
    -0.06
    åĶ¯ä¸Ģ
    -0.06
    POSITIVE LOGITS
     roughly
    0.10
    大èĩ´
    0.09
    ç±»æ¯Ķ
    0.09
     Estimate
    0.08
    æľĢ大æīŃ磩
    0.08
    rough
    0.08
     estimates
    0.08
     estimate
    0.08
    .getSimpleName
    0.08
    大约æĺ¯
    0.08
    Activations Density 0.013%

    No Known Activations