© 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. 18583
    Prev
    Next
    INDEX
    Explanations

    gitlog option --SFoo, ring extensions, gitlog option --SF, ring extensions

    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
    zet
    -0.06
    aro
    -0.06
    ium
    -0.06
    ĥĿ
    -0.06
    LAB
    -0.06
    avis
    -0.06
     Perf
    -0.06
    agle
    -0.06
    zia
    -0.06
    缮ä¸į
    -0.06
    POSITIVE LOGITS
    appers
    0.08
    ötz
    0.07
    tingham
    0.07
    bsites
    0.07
    :\/\/
    0.07
    onnen
    0.07
    .IsActive
    0.07
    åħ¶æŀĹ
    0.07
    æĨ¬
    0.07
    evity
    0.07
    Activations Density 0.027%

    No Known Activations