© 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. 3736
    Prev
    Next
    INDEX
    Explanations

    explaining how or why something is done

    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
    olit
    -0.08
     instead
    -0.06
     Situation
    -0.06
    让æĪijä»¬åľ¨
    -0.06
     bother
    -0.06
    æľĪæľ«
    -0.06
    以åIJİåĨį
    -0.06
     situation
    -0.06
    åį³ä»¥
    -0.06
    æīįèĥ½åľ¨
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģäºĨ解
    0.08
    ä¸įå¾Ĺ使çĶ¨
    0.08
    ä¸įä¹ı
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.08
     dabei
    0.08
    è¿ijåįĥ
    0.08
     Dazu
    0.08
     Dabei
    0.08
    ython
    0.08
    avras
    0.08
    Activations Density 0.143%

    No Known Activations