© 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. 46719
    Prev
    Next
    INDEX
    Explanations

    promisify or Abcd prefixes

    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
    çłĶ究æīĢ
    -0.07
    ä¸įåĽł
    -0.07
    enças
    -0.07
    kest
    -0.07
    ä¸Ģ身
    -0.07
    åIJĽå®ī
    -0.07
    eres
    -0.07
    dav
    -0.07
    çļĦåľ°åĿĢ
    -0.07
    å¦ĩ产åĮ»éĻ¢
    -0.06
    POSITIVE LOGITS
    inate
    0.07
    Fmt
    0.07
    æķ¢
    0.07
    paginate
    0.07
    can
    0.07
    kah
    0.06
    voi
    0.06
    ØŃÙĪÙĦ
    0.06
    ụn
    0.06
    æ³¢ç½Ĺ
    0.06
    Activations Density 0.004%

    No Known Activations