© 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. 18607
    Prev
    Next
    INDEX
    Explanations

    sequencesoutsideresultrecognizeimplemented bytake

    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
     '&#
    -0.08
    ä¸Ģå¤ķ
    -0.07
    æķĻ书
    -0.07
    ä¸įå°ı
    -0.07
    èĹIJ
    -0.07
    @$
    -0.07
    æĸ¯åį¡
    -0.07
    尼奥
    -0.07
     vog
    -0.07
    LEC
    -0.07
    POSITIVE LOGITS
    çļĦä»»ä½ķ
    0.08
     Wer
    0.08
    ä»»ä½ķä¸ľè¥¿
    0.08
     cualquiera
    0.08
    ä»»ä½ķ
    0.08
    以任ä½ķ
    0.07
    ä»»ä½ķå½¢å¼ıçļĦ
    0.07
     Qualquer
    0.07
     Andersen
    0.07
    unkt
    0.07
    Activations Density 0.112%

    No Known Activations