© 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. 18130
    Prev
    Next
    INDEX
    Explanations

    box + ylic / ym / yl / yle

    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
    Ø©
    -0.09
    èģĮå®Ī
    -0.07
    ropolit
    -0.07
    ãĤĵãģ«
    -0.07
    enty
    -0.07
    erto
    -0.07
    ´
    -0.07
    ãĤīãģĭ
    -0.07
    ensely
    -0.07
    stras
    -0.06
    POSITIVE LOGITS
    ate
    0.09
    lah
    0.08
    ylic
    0.08
    ¨
    0.08
    ylation
    0.08
    dit
    0.08
    ibbean
    0.08
    er
    0.07
    elain
    0.07
    iness
    0.07
    Activations Density 0.008%

    No Known Activations