© 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. 45969
    Prev
    Next
    INDEX
    Explanations

    report and recommendation

    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
    avn
    -0.07
    績
    -0.07
    <|box_end|>
    -0.07
    ilde
    -0.06
    avors
    -0.06
    ayload
    -0.06
    çİīæłij
    -0.06
    檻
    -0.06
    ürg
    -0.06
    ccount
    -0.06
    POSITIVE LOGITS
    羣çļĦ好
    0.08
    лÑĸн
    0.08
    линг
    0.08
    phu
    0.08
    羣çļĦ太
    0.07
    å¾ĢæľŁåĽŀ顾
    0.07
    ç½ĹæĽ¼
    0.07
    æĿijæĿijæ°ij
    0.07
    arana
    0.07
    åıĤä¸İè¯Ħ论
    0.07
    Activations Density 1.241%

    No Known Activations