© 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. 62127
    Prev
    Next
    INDEX
    Explanations

    calculating derivatives and solving equations

    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
    /conf
    -0.07
    bedo
    -0.07
    uct
    -0.07
    ারà§į
    -0.07
    andong
    -0.07
    æĬĬ
    -0.07
    æĬĬéĤ£
    -0.06
    ÉĻrb
    -0.06
    å°Ĩè¿Ļ个
    -0.06
    .instant
    -0.06
    POSITIVE LOGITS
    몽
    0.07
    icola
    0.07
    nä
    0.07
    gger
    0.07
     massively
    0.07
    неÑĤа
    0.07
    æĪ·æĪ·
    0.06
    igno
    0.06
    å¿ĹæĪIJ
    0.06
    å¿ĥæĥ³äºĭæĪIJ
    0.06
    Activations Density 0.083%

    No Known Activations