© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29872
    Prev
    Next
    INDEX
    Explanations

    successfully, early, there

    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
    Squared
    -0.08
    eschi
    -0.08
    æľ¬æĸĩæĿ¥èĩª
    -0.07
    ivet
    -0.07
    åĬ¡
    -0.07
    worm
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    stö
    -0.06
    é¾Ļçİĭ
    -0.06
    )$/
    -0.06
    POSITIVE LOGITS
    .Simple
    0.07
    aning
    0.07
    dex
    0.07
    æ£Ħ
    0.06
    anes
    0.06
    HY
    0.06
    çļĦæĥħæĻ¯
    0.06
    rogen
    0.06
    èī¯å¥½çļĦåŁºç¡Ģ
    0.06
    Simple
    0.06
    Activations Density 0.002%

    No Known Activations