© 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. 40328
    Prev
    Next
    INDEX
    Explanations

    amazon.com and years-old

    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
    åIJİéĢĢ
    -0.07
    _selector
    -0.07
     proviso
    -0.06
    indr
    -0.06
    ãģŀ
    -0.06
     optics
    -0.06
     ?
    -0.06
     ,
    -0.06
     /
    -0.06
    VICE
    -0.06
    POSITIVE LOGITS
    izard
    0.09
    NEY
    0.08
    åı¯èĥ½è¦ģ
    0.08
    çªŁ
    0.08
    为ä»Ģä¹Ī说
    0.08
    _UNDER
    0.08
    西æĸ¯
    0.07
    бÑĥдÑĮ
    0.07
     nháºŃp
    0.07
     inferred
    0.07
    Activations Density 0.003%

    No Known Activations