© 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. 9422
    Prev
    Next
    INDEX
    Explanations

    class="

    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
    ernas
    -0.07
    ernals
    -0.07
    izz
    -0.06
    ALO
    -0.06
    çļĦåħ¨éĿ¢
    -0.06
    é«ĺçĤ¹
    -0.06
    /mock
    -0.06
    annis
    -0.06
    ারà§ĩ
    -0.06
    erset
    -0.06
    POSITIVE LOGITS
    ylv
    0.09
    olie
    0.07
    itez
    0.07
    WithDuration
    0.07
    大夫
    0.07
    ISMATCH
    0.07
    pst
    0.07
    ãĤĬãģĻãĤĭ
    0.07
    oute
    0.07
    OUNTER
    0.07
    Activations Density 0.027%

    No Known Activations