© 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. 40763
    Prev
    Next
    INDEX
    Explanations

    class or tags

    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
    æľīåIJį
    -0.08
    iv
    -0.08
    ori
    -0.07
    kori
    -0.07
    饰æ¼Ķ
    -0.07
    æ¼Ķ
    -0.07
    对åºĶ
    -0.07
    åĭī
    -0.07
    ivs
    -0.07
    çģŃ
    -0.07
    POSITIVE LOGITS
    arcy
    0.07
    wana
    0.07
    ypad
    0.06
    itano
    0.06
    arque
    0.06
    åıĤåĬłå·¥ä½ľ
    0.06
    à§ĩষ
    0.06
    身ä½ĵçĬ¶åĨµ
    0.06
    T
    0.06
    ztat
    0.06
    Activations Density 0.297%

    No Known Activations