© 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. 39617
    Prev
    Next
    INDEX
    Explanations

    ordering or sorting items

    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
    è½°
    -0.08
    è·ŁåĽ¢
    -0.08
    转载请注æĺİåĩºå¤Ħ
    -0.08
    anski
    -0.08
    为è°ģ
    -0.08
    igno
    -0.08
    AYOUT
    -0.08
    klam
    -0.08
     opro
    -0.08
    etty
    -0.07
    POSITIVE LOGITS
    ç§
    0.06
    èĮ¨
    0.06
    ä¸İ该
    0.06
    pon
    0.06
    è¶ħ
    0.06
    uet
    0.06
    åħ·
    0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.06
    为该
    0.06
    ä¸įåı¯æĢķ
    0.06
    Activations Density 0.038%

    No Known Activations