© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    header, weather, mission, album, canceled, water, copyright, materials, title

    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
    TestFixture
    -0.07
    丹丹
    -0.07
    rava
    -0.07
    ieur
    -0.06
    éĿĸ
    -0.06
    路人
    -0.06
    ellig
    -0.06
    arters
    -0.06
    å´İ
    -0.06
    æ¿ĢçĥĪ
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    zinho
    0.07
    åı¯äº²
    0.06
    æµ·å®ģ
    0.06
    ụt
    0.06
    ä¸ĵäººè´Łè´£
    0.06
    zinha
    0.06
    Nil
    0.06
    è¦ģä¹Ī
    0.06
    Activations Density 0.061%

    No Known Activations