© 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. 33733
    Prev
    Next
    INDEX
    Explanations

    positioning, installing, inserting

    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
    ä¸įå®ļæľŁ
    -0.08
    åĪĩãĤĬ
    -0.08
     Produce
    -0.07
    ä¸įæŃ»
    -0.07
    _outputs
    -0.07
    ä¸įåĪĨ
    -0.07
     dereg
    -0.07
    æ´»è·ĥ
    -0.07
     chained
    -0.07
    çī¹éĴ¢
    -0.07
    POSITIVE LOGITS
    å°±ä½į
    0.13
    æĹłåıį
    0.10
     snug
    0.09
     assembled
    0.09
     assembly
    0.09
     positioning
    0.08
     insertion
    0.08
    åį³åı¯å®ĮæĪIJ
    0.08
    è´´åIJĪ
    0.08
    æŃ£ç¡®
    0.08
    Activations Density 0.300%

    No Known Activations