© 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. 48912
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    ()
    -0.06
    vi
    -0.06
     A
    -0.06
    ot
    -0.06
     Ste
    -0.06
    ajs
    -0.06
    缴
    -0.06
    etch
    -0.06
    èĩª
    -0.06
     ar
    -0.06
    POSITIVE LOGITS
    ilup
    0.09
    ÙĪÙĬا
    0.08
    uard
    0.08
    icino
    0.08
    coa
    0.08
     Docente
    0.08
    .TryParse
    0.08
    ÙĪÛĮÙĩ
    0.08
    ded
    0.08
    angers
    0.08
    Activations Density 0.006%

    No Known Activations