© 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. 42649
    Prev
    Next
    INDEX
    Explanations

    setting parameters or declaring variables

    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
     Zaj
    -0.07
    æĭīéĩĮ
    -0.06
    å¤ļçľĭ
    -0.06
    çĭ¬è¡Į
    -0.06
     himself
    -0.06
    Away
    -0.06
    ince
    -0.06
    åħ±åº¦
    -0.06
     ÄIJa
    -0.06
    jal
    -0.06
    POSITIVE LOGITS
    åŃĺåľ¨çļĦ
    0.11
     exists
    0.10
    çļĦåŃĺåľ¨
    0.10
    ä¸įåŃĺåľ¨
    0.10
    Exists
    0.10
    _exists
    0.10
    Nullable
    0.09
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
     None
    0.09
    -none
    0.09
    Activations Density 0.303%

    No Known Activations