© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    author information

    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
    ungk
    -0.07
    åħį
    -0.07
    使çĶ¨è¯¥
    -0.07
    uesa
    -0.06
    æĭĸ
    -0.06
    æĭĸçĿĢ
    -0.06
     ung
    -0.06
    è¿Ļæĺ¯ä¸ª
    -0.06
    åIJ«ç³Ĭ
    -0.06
     phán
    -0.06
    POSITIVE LOGITS
    verbosity
    0.08
    ToFit
    0.08
    åIJĦéłħ
    0.07
     promptly
    0.07
    á´ł
    0.07
    -INF
    0.07
    ê¼
    0.07
    æłĢ
    0.07
    quis
    0.07
    _responses
    0.07
    Activations Density 0.007%

    No Known Activations