© 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. 42646
    Prev
    Next
    INDEX
    Explanations

    ligands or Etest

    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
    æĸĩçIJĨ
    -0.07
     nasc
    -0.07
    _except
    -0.07
    æľªç»ı
    -0.07
     useful
    -0.07
    wcs
    -0.06
     Useful
    -0.06
    chie
    -0.06
    è¾ĸ
    -0.06
    _sk
    -0.06
    POSITIVE LOGITS
    TextInput
    0.08
    EDIUM
    0.08
    éĿ¢å¯¹éĿ¢
    0.08
     modifiers
    0.07
     khơi
    0.07
     Fischer
    0.07
    æİĴä½į
    0.07
    åĮħåĽ´
    0.07
    æīĭä¸Ń
    0.07
    缸å¤Ħ
    0.07
    Activations Density 0.002%

    No Known Activations