© 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. 51545
    Prev
    Next
    INDEX
    Explanations

    speaker or compiler

    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
    anker
    -0.08
    éģĵè¿ľ
    -0.08
    ä¸Ģ模
    -0.08
    æł¹æľ¬ä¸įæĺ¯
    -0.07
    ayne
    -0.07
    ذار
    -0.07
    quires
    -0.07
    awe
    -0.07
    æģį
    -0.07
    ä¹Łä¸įä¸Ģæł·
    -0.07
    POSITIVE LOGITS
    æĹ¢çĦ¶
    0.10
    æĪijä»¬çĽ¸ä¿¡
    0.09
    æĹ¢çĦ¶æĺ¯
    0.09
    åĢ¼å¾Ĺä¿¡èµĸ
    0.09
     presumably
    0.09
    çĽ¸ä¿¡
    0.08
     reputable
    0.08
    就说æĺİ
    0.08
    å¿ħæľī
    0.08
    说æĺİ
    0.08
    Activations Density 0.101%

    No Known Activations