© 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. 32593
    Prev
    Next
    INDEX
    Explanations

    research, elsewhere, tab, post

    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
    éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    -0.07
    awa
    -0.07
    ayi
    -0.06
     CONCE
    -0.06
    ¤
    -0.06
    ä¸Ģ天天
    -0.06
    ormal
    -0.06
    è¦ģä¸į
    -0.06
    ebr
    -0.06
    à¸Ĺà¸ĺ
    -0.06
    POSITIVE LOGITS
    иÑĤо
    0.08
     resulting
    0.08
    ç»ı
    0.08
    å¼ķãģį
    0.08
    auh
    0.08
    abad
    0.08
    ç»ıçIJĨ
    0.08
    ouc
    0.08
    etten
    0.08
    æĬľãģį
    0.07
    Activations Density 0.044%

    No Known Activations