© 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. 50775
    Prev
    Next
    INDEX
    Explanations

    examples and applications

    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
    è¦ģä¹Īæĺ¯
    -0.08
    è¦ģä¹Ī
    -0.08
     Either
    -0.08
     either
    -0.08
    -inf
    -0.07
    either
    -0.07
    ashian
    -0.07
     Ø¥Ùħا
    -0.07
    Either
    -0.07
    åŃ¤å²Ľ
    -0.07
    POSITIVE LOGITS
    为ä¾ĭ
    0.11
    çĤºä¾ĭ
    0.09
     example
    0.09
    example
    0.09
    Example
    0.08
     Example
    0.08
     typical
    0.07
    empio
    0.07
    /example
    0.07
    ehm
    0.07
    Activations Density 0.265%

    No Known Activations