© 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. 61455
    Prev
    Next
    INDEX
    Explanations

    clues

    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
    çı
    -0.09
    å¾Ĺ天
    -0.08
    uale
    -0.08
    vist
    -0.08
    éĺ¿æĭī伯
    -0.08
    Ð¢ÐŁ
    -0.08
    ongi
    -0.08
    ész
    -0.07
    king
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
    POSITIVE LOGITS
     clue
    0.07
    ä»Ķç»Ĩçľĭ
    0.06
    ä»Ķç»Ĩ
    0.06
    lav
    0.06
    ask
    0.06
    éĶIJæĦı
    0.06
     clues
    0.06
    大æĢĴ
    0.06
     Heid
    0.06
    è®¤çľŁçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations