© 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. 28762
    Prev
    Next
    INDEX
    Explanations

    twinkle star, lonely cloud

    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
    agu
    -0.08
    以德
    -0.08
    ntl
    -0.06
    欣
    -0.06
    okit
    -0.06
    äºŃäºŃ
    -0.06
    踢
    -0.06
    TEL
    -0.06
     Pend
    -0.06
    ç¼ĺæķħ
    -0.06
    POSITIVE LOGITS
    ÙģÙĩ
    0.08
    ikian
    0.08
    erg
    0.07
    ä¹į
    0.07
    åt
    0.07
    atinum
    0.07
    æĪijçļĦå¿ĥ
    0.07
    Cors
    0.07
    åįģäºĶç«ł
    0.07
    isian
    0.07
    Activations Density 0.076%

    No Known Activations