© 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. 24692
    Prev
    Next
    INDEX
    Explanations

    wear, toxicity, or noise

    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
    eran
    -0.08
    apte
    -0.08
    æĢ
    -0.08
    就好æ¯Ķ
    -0.07
     dern
    -0.07
    affer
    -0.07
    erie
    -0.07
    <quote
    -0.07
     Sor
    -0.07
    _MISSING
    -0.07
    POSITIVE LOGITS
    ä¹ŁåĽłä¸º
    0.09
    ä¹ŁæľīåĪ©äºİ
    0.09
    çŃīåħ¶ä»ĸ
    0.07
    æľīåĪ©äºİ
    0.07
    ä¹ŁåĽł
    0.07
    çŃīæĸ¹éĿ¢çļĦ
    0.07
    åĪ©äºİ
    0.07
    enco
    0.07
    .Empty
    0.06
    åĽłä¸ºåıªæľī
    0.06
    Activations Density 0.188%

    No Known Activations