© 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. 24120
    Prev
    Next
    INDEX
    Explanations

    formatting like `[ ]` or `: `

    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
    OSS
    -0.09
    otte
    -0.07
    quo
    -0.07
    ODO
    -0.07
    OAD
    -0.06
    cono
    -0.06
    óra
    -0.06
    ampp
    -0.06
    nob
    -0.06
    èģĭ
    -0.06
    POSITIVE LOGITS
     forskning
    0.08
    OwnProperty
    0.08
    æ±Ĥ羣
    0.07
    åı¥åı¥
    0.07
    apatan
    0.07
    ULATE
    0.07
    æĭ¬
    0.07
    θεν
    0.07
    acente
    0.07
    owell
    0.07
    Activations Density 0.001%

    No Known Activations