© 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. 12261
    Prev
    Next
    INDEX
    Explanations

    keywords and introduction sections

    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
    <|box_end|>
    -0.09
    约å®ļ
    -0.08
    ç³ľ
    -0.07
    æ¸Ķ
    -0.07
    åºIJ
    -0.07
    æĪijçıŃ
    -0.07
    æľīä¸Ģ份
    -0.07
    ä¸Ģ份
    -0.07
    immer
    -0.07
    ingers
    -0.07
    POSITIVE LOGITS
    åħ³éĶ®è¯į
    0.10
     Keywords
    0.09
    åħ³éĶ®åŃĹ
    0.07
    _abstract
    0.07
     keywords
    0.07
    Keywords
    0.07
    ãĤŃãĥ¼ãĥ¯ãĥ¼ãĥī
    0.07
     Introduction
    0.07
     Citation
    0.07
    utton
    0.07
    Activations Density 0.263%

    No Known Activations