© 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. 16570
    Prev
    Next
    INDEX
    Explanations

    plan

    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
    abouts
    -0.09
    icana
    -0.09
    plevel
    -0.08
    ÑĩеÑĢед
    -0.08
    een
    -0.08
    entifier
    -0.08
    лик
    -0.07
    pta
    -0.07
    ereum
    -0.07
    eenth
    -0.07
    POSITIVE LOGITS
    itud
    0.10
     ìĪĺ립
    0.09
    eworthy
    0.09
    entiful
    0.09
    ãĤıãĤĬãģ«
    0.08
    seudo
    0.08
    ares
    0.08
    áŁĭ
    0.08
    ãĤĴç«ĭãģ¦
    0.08
    fully
    0.08
    Activations Density 0.033%

    No Known Activations