© 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. 22279
    Prev
    Next
    INDEX
    Explanations

    URL paths and punctuation

    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
    -next
    -0.07
    åIJijä¸Ĭ级
    -0.07
    azzo
    -0.07
    crest
    -0.07
    æĪIJæľ¬ç®¡çIJĨ
    -0.07
     NEXT
    -0.07
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    -0.07
    лÑĥб
    -0.07
    .Next
    -0.07
    æ½®æ±IJ
    -0.06
    POSITIVE LOGITS
    enn
    0.07
    乡
    0.07
    agger
    0.07
    vn
    0.07
    cas
    0.06
    ä¿ĥ
    0.06
    æµĨ
    0.06
    eli
    0.06
    oes
    0.06
     Eag
    0.06
    Activations Density 0.236%

    No Known Activations