© 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. 15557
    Prev
    Next
    INDEX
    Explanations

    symbols list item markers

    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
     дело
    -0.07
     $__
    -0.06
    ç»Ĩå¿ĥçļĦ
    -0.06
    éľĦ
    -0.06
    aeda
    -0.06
    éĴ£éĩij
    -0.06
    æĸĮ
    -0.06
    åĨķ
    -0.06
    planation
    -0.06
    engk
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.10
     наконеÑĨ
    0.08
     enfin
    0.08
     infine
    0.08
    çĤ¹æĺ¯
    0.07
    åĭ¤åĭ¤æģ³æģ³
    0.07
    èĢ³çĨŁèĥ½è¯¦
    0.07
    åħ¶ä»ĸæĸ¹å¼ı
    0.07
    åħ¶å®ĥ
    0.07
    åĢĺèĭ¥
    0.07
    Activations Density 0.291%

    No Known Activations