© 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. 58565
    Prev
    Next
    INDEX
    Explanations

    incrementing or resetting numeric 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
    æĪŁ
    -0.07
    çŀij
    -0.07
    éĶ¦æłĩ
    -0.07
    _attempts
    -0.07
    thus
    -0.07
    çŃĶé¢ĺåį¡
    -0.07
    æ´ĭ
    -0.07
     Crest
    -0.07
    гоÑĢод
    -0.07
    å½ĵå±ŀ
    -0.06
    POSITIVE LOGITS
    èĨ¨
    0.07
    -sum
    0.07
     sum
    0.07
    è´¡çĮ®
    0.07
    |int
    0.07
     -=
    0.07
     +=
    0.07
    æĢ»çļĦ
    0.07
     contributions
    0.06
    æµģæ°´
    0.06
    Activations Density 0.006%

    No Known Activations