© 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. 2801
    Prev
    Next
    INDEX
    Explanations

    article/post identifiers

    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
    éľĵ
    -0.07
    lý
    -0.07
    _LS
    -0.07
    .qq
    -0.07
    ãģ¨ãģĨ
    -0.07
    æ»´æ°´
    -0.06
    ä¸įå¾Ĺ使çĶ¨
    -0.06
    -conf
    -0.06
    æ¦ľ
    -0.06
    ÅĤoż
    -0.06
    POSITIVE LOGITS
    ither
    0.08
    æľĿçļĦ
    0.07
    indle
    0.07
     Ivory
    0.07
     gem
    0.07
    ä¸Ģè¾Ī
    0.07
    htdocs
    0.06
    agak
    0.06
    bris
    0.06
    ario
    0.06
    Activations Density 0.022%

    No Known Activations