© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23444
    Prev
    Next
    INDEX
    Explanations

    steel, silicon, oxide, substrate, slate, surfaces

    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
    csi
    -0.08
    ä¸Ńæľī
    -0.07
    å¾ĺ
    -0.07
    ariat
    -0.07
    ä¸ŃåĮħåIJ«
    -0.07
     Reese
    -0.07
    éĩĮéĿ¢æľī
    -0.07
    olog
    -0.07
     êm
    -0.07
    ikle
    -0.07
    POSITIVE LOGITS
    表éĿ¢
    0.15
     surface
    0.14
    表éĿ¢çļĦ
    0.14
     surfaces
    0.13
    surface
    0.11
     Surface
    0.11
    è£¸éľ²
    0.11
    Surface
    0.11
    çļĦ表éĿ¢
    0.10
     повеÑĢÑħноÑģÑĤи
    0.10
    Activations Density 0.344%

    No Known Activations