© 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. 4151
    Prev
    Next
    INDEX
    Explanations

    labor relations board

    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
    onger
    -0.08
     Estad
    -0.08
    precated
    -0.08
    <|box_end|>
    -0.07
    jeg
    -0.07
     flo
    -0.07
    ãģ¡ãģª
    -0.07
     camb
    -0.07
    åı£è¢ĭ
    -0.07
    å¿Ĺ
    -0.07
    POSITIVE LOGITS
     interpretations
    0.08
     Corte
    0.08
     interpret
    0.08
     interpreting
    0.08
    æĹłåıĮ
    0.07
    æģ©æĸ¯
    0.07
     interpretation
    0.07
     interpretar
    0.07
     Interpret
    0.07
     interpr
    0.07
    Activations Density 0.012%

    No Known Activations