© 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. 9325
    Prev
    Next
    INDEX
    Explanations

    ';', '.', 'self', 'class', 'alphanumeric'

    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
    dbe
    -0.09
    æ¸Ĭ
    -0.08
    sdale
    -0.07
    omás
    -0.07
    åĴĮéĩįçĤ¹
    -0.07
    \":\"
    -0.07
    ecca
    -0.07
    Extras
    -0.07
    ystack
    -0.07
    æıIJè¦ģ
    -0.07
    POSITIVE LOGITS
    åıį
    0.08
    ajas
    0.07
    ×IJ×ķת
    0.07
    atten
    0.07
    æĥħå½¢çļĦ
    0.07
     erroneous
    0.06
    byn
    0.06
    nyder
    0.06
    忽
    0.06
    izont
    0.06
    Activations Density 0.001%

    No Known Activations