© 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. 27535
    Prev
    Next
    INDEX
    Explanations

    specializes in, solutions for, evolved in

    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
    ä¸įæ²»
    -0.07
     ‘’
    -0.07
    æŁIJ
    -0.07
     somehow
    -0.07
    [s
    -0.07
    (s
    -0.06
    ¬
    -0.06
    ä¸Ģç«Ļ
    -0.06
     dear
    -0.06
    ο
    -0.06
    POSITIVE LOGITS
    annie
    0.09
    å¹´çļĦåİĨåı²
    0.08
    vary
    0.08
    itora
    0.07
    umba
    0.07
    å¹´å¹³åĿĩ
    0.07
    åıĺçļĦ
    0.07
    vej
    0.07
    elaar
    0.07
    _accum
    0.07
    Activations Density 0.010%

    No Known Activations