© 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. 21311
    Prev
    Next
    INDEX
    Explanations

    fraction, amounts, coefficient, numbering, occupationally

    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
    anch
    -0.08
    ĵĴ
    -0.08
    带äºĨ
    -0.08
     adaptations
    -0.08
    @mail
    -0.07
    åĭ§
    -0.07
    =@
    -0.07
    obox
    -0.07
    ÏĢά
    -0.07
    ecker
    -0.07
    POSITIVE LOGITS
    åįłæĢ»
    0.09
    åįł
    0.08
    ä½
    0.07
    gil
    0.07
    çļĦæ¯Ķä¾ĭ
    0.07
    æ¯Ķä¾ĭ
    0.07
    æ¯Ķä¾ĭçļĦ
    0.06
    ÑģÑĤина
    0.06
    ä¸įæĪIJ
    0.06
    _ARG
    0.06
    Activations Density 0.003%

    No Known Activations