© 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. 31313
    Prev
    Next
    INDEX
    Explanations

    listing repetitions

    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
    кÑĬ
    -0.07
    ä¸Ī
    -0.07
    ymbol
    -0.07
    profiles
    -0.07
    ,float
    -0.07
    ç¾İ好çĶŁæ´»çļĦ
    -0.07
    æľīå½¢
    -0.06
     Flo
    -0.06
    apis
    -0.06
    _IO
    -0.06
    POSITIVE LOGITS
    trag
    0.08
    çIJ³å¨ľ
    0.08
    à¸Ĥ
    0.07
    stein
    0.07
    yesi
    0.07
    zey
    0.07
    çıĪ
    0.07
    zes
    0.07
    è¨Ī
    0.07
    åıĮéĿ¢
    0.07
    Activations Density 0.010%

    No Known Activations