© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20727
    Prev
    Next
    INDEX
    Explanations

    length and dimensions

    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
    uf
    -0.08
    æĢģ
    -0.07
    ulous
    -0.07
    宿
    -0.07
    è°
    -0.07
    -powered
    -0.07
    ele
    -0.06
    è«
    -0.06
    iat
    -0.06
    .yy
    -0.06
    POSITIVE LOGITS
    尺寸
    0.10
    ADIUS
    0.09
    è·ĿéĽ¢
    0.09
    éķ¿åº¦
    0.09
    éķ¿åº¦çļĦ
    0.09
     length
    0.08
    尺寸çļĦ
    0.08
    è¶Ĭéķ¿
    0.08
    ä¸Ī
    0.08
     dimensions
    0.08
    Activations Density 0.002%

    No Known Activations