© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    magenta, spark, movement, volcanos, python, pea, Kumar

    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
    Extern
    -0.08
    artigen
    -0.07
    ç¼ĵç¼ĵçļĦ
    -0.07
    ahuan
    -0.07
    zaam
    -0.07
    eated
    -0.07
     EITHER
    -0.07
    anness
    -0.07
    λÏī
    -0.07
    รวà¸ĩ
    -0.07
    POSITIVE LOGITS
    åĺĽ
    0.09
     же
    0.09
     zaÅĽ
    0.08
     vs
    0.08
     ведÑĮ
    0.07
     enim
    0.07
    ÙĮ
    0.07
    ä¹ĭ为
    0.07
     enfin
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    Activations Density 0.964%

    No Known Activations