© 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. 41816
    Prev
    Next
    INDEX
    Explanations

    variables and code 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
    emos
    -0.09
    èİ«
    -0.08
    ä¸įå¾Ĺä½İäºİ
    -0.07
     Grie
    -0.07
    icable
    -0.07
    TC
    -0.07
    utica
    -0.07
    UDGE
    -0.07
    çĪ±åIJĥ
    -0.07
    ëį§
    -0.07
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.07
    หมาย
    0.06
    جÙħØ©
    0.06
    éĥ¨å§Ķ
    0.06
    æĭĨ
    0.06
    यà¥ĩ
    0.06
    å¤ĩéĢī
    0.06
    äºĶå®ĺ
    0.06
    peaker
    0.06
    agher
    0.06
    Activations Density 0.016%

    No Known Activations