© 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. 10379
    Prev
    Next
    INDEX
    Explanations

    infinitesimal, small, zero, thin

    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
    fully
    -0.10
    ulich
    -0.10
    ported
    -0.09
    unker
    -0.09
    illow
    -0.09
    chter
    -0.08
    porté
    -0.08
    FUL
    -0.08
    tsky
    -0.08
    éĽ³
    -0.08
    POSITIVE LOGITS
    esimal
    0.08
    е
    0.07
    aller
    0.07
    ary
    0.07
    aneous
    0.07
    enberg
    0.07
    ly
    0.07
    ith
    0.07
    åĮĸçļĦ
    0.06
    amente
    0.06
    Activations Density 0.002%

    No Known Activations