© 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. 51634
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    ä¸ī大
    -0.12
    ä¸īèĢħ
    -0.11
    ä¸īçĤ¹
    -0.11
    è¿Ļä¸ī
    -0.11
    ä¸ī项
    -0.11
     thirds
    -0.11
    ä¸ī人
    -0.10
    ä¸īéĥ¨æĽ²
    -0.10
    è¿Ļ两个
    -0.10
     ketiga
    -0.10
    POSITIVE LOGITS
    åħ«ä¸ª
    0.14
    ä¸ĥ个
    0.14
     eight
    0.11
    åħŃ个
    0.11
    äºĶ个
    0.11
    åħŃä½į
    0.11
    seven
    0.11
     seven
    0.11
    ABCDEFG
    0.11
    åįģ个
    0.11
    Activations Density 0.611%

    No Known Activations