© 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. 29931
    Prev
    Next
    INDEX
    Explanations

    reflection, scattering, passed through

    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
    转åŀĭ
    -0.07
    еÑĩÑĮ
    -0.07
    IFY
    -0.07
    æݨ广
    -0.07
    æĹłæ³ķ满足
    -0.07
    .assign
    -0.06
    ä¸İæľ¬ç«Ļ
    -0.06
    .dev
    -0.06
    emp
    -0.06
    itante
    -0.06
    POSITIVE LOGITS
    两次
    0.08
    boden
    0.08
    åıªæľīä¸Ģ次
    0.08
     взаимодейÑģÑĤви
    0.07
    çļĦåıĮéĩį
    0.07
    å¤ļ次
    0.07
    æĩ¦
    0.07
     Interaction
    0.07
    oubl
    0.07
    rever
    0.07
    Activations Density 0.003%

    No Known Activations