© 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. 3258
    Prev
    Next
    INDEX
    Explanations

    technical or formal ending phrase

    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
    件äºĭ
    -0.08
    ross
    -0.07
     ISTIT
    -0.07
     Ø®ÙĬر
    -0.07
    osos
    -0.07
     surfaced
    -0.07
    (Str
    -0.07
    hirt
    -0.07
    quals
    -0.07
     quits
    -0.07
    POSITIVE LOGITS
    éªĭ
    0.08
    reif
    0.07
    å¾Ĺå¿ĥ
    0.07
    ENUM
    0.07
    娲
    0.07
    çļĦåİŁåĽłæĺ¯
    0.06
     hái
    0.06
    бÑĢан
    0.06
    ãģĹãģŁãģ®ãģ¯
    0.06
    æĿ¥è¯´è¯´
    0.06
    Activations Density 0.004%

    No Known Activations