© 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. 3863
    Prev
    Next
    INDEX
    Explanations

    unless clauses

    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
    venu
    -0.08
     OPTIONAL
    -0.08
    è¾ĸ
    -0.07
    лиз
    -0.07
    кин
    -0.07
    _BC
    -0.07
    yre
    -0.07
    æ®ĭ念ãģªãģĮãĤī
    -0.07
    æŨ
    -0.07
    åıįæŃ£
    -0.07
    POSITIVE LOGITS
     unless
    0.09
    unless
    0.09
    éĻ¤éĿŀ
    0.09
    Unless
    0.07
     Unless
    0.07
    _framework
    0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.07
    ongo
    0.07
    oto
    0.07
    olum
    0.07
    Activations Density 0.033%

    No Known Activations