© 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. 56997
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    æ³Ĺ
    -0.08
    æĭ¬
    -0.07
    abbr
    -0.07
    .dynamic
    -0.07
    å§Ķ
    -0.07
    æķ¢
    -0.07
    uca
    -0.07
    lán
    -0.07
    åıĬåĪ©æģ¯
    -0.06
     Ãļnico
    -0.06
    POSITIVE LOGITS
    çħ§æł·
    0.09
    ä¹Łåı¯ä»¥æĺ¯
    0.09
    çŃīåħ¶ä»ĸ
    0.09
    æľīå¾Īå¤ļç§į
    0.08
    åį³ä½¿
    0.08
    åıªè¦ģèĥ½
    0.08
    åı¯ä»¥æĺ¯
    0.08
     simply
    0.08
     even
    0.08
     without
    0.08
    Activations Density 0.049%

    No Known Activations