© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59959
    Prev
    Next
    INDEX
    Explanations

    prior experience or background

    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
    Negative Logits
    è´®
    -0.07
    åħ¶äºº
    -0.07
    lying
    -0.06
    ä»İæł¹æľ¬ä¸Ĭ
    -0.06
     Incorporated
    -0.06
    ::__
    -0.06
    åijĹ
    -0.06
     Zas
    -0.06
    icamente
    -0.06
    ÄIJT
    -0.06
    POSITIVE LOGITS
     but
    0.09
    uff
    0.08
     enough
    0.07
    anton
    0.07
    inker
    0.07
    åħ·å¤ĩä¸Ģå®ļçļĦ
    0.07
     ÙĨس
    0.07
    à¸ĵะ
    0.07
    ä½Ĩ并ä¸į
    0.07
    but
    0.07
    Activations Density 0.011%

    No Known Activations