© 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. 27464
    Prev
    Next
    INDEX
    Explanations

    tasks and costs

    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
    isiv
    -0.07
    inspace
    -0.06
    xyz
    -0.06
     ÙĨÚ¯
    -0.06
     inoltre
    -0.06
    áĥ¡
    -0.06
    ï¼Ŀï¼Ŀ
    -0.06
    ialect
    -0.06
    ãģĦãģ¡
    -0.06
    arith
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.11
    ãģ¨ãĤĤãģ«
    0.09
     vÃł
    0.09
    ãģĿãģĹãģ¦
    0.09
     à¹ģละ
    0.08
    ,and
    0.08
     à¤Ķर
    0.08
     and
    0.08
     и
    0.08
    åĴĮ
    0.08
    Activations Density 0.328%

    No Known Activations