© 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. 15204
    Prev
    Next
    INDEX
    Explanations

    collect, greatest, highest, prime, initiated, undertaken

    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
    èĺĭ
    -0.08
    inator
    -0.08
    ueux
    -0.08
    VAR
    -0.08
    entes
    -0.08
    lada
    -0.08
    红楼
    -0.08
     мани
    -0.08
    端åĪ°
    -0.08
     tim
    -0.07
    POSITIVE LOGITS
    itz
    0.07
    éĢIJä¸Ģ
    0.07
    ed
    0.07
    æİ¢
    0.06
    -
    0.06
    |
    0.06
    arre
    0.06
    _UPDATED
    0.06
    次çļĦ
    0.06
    åĮ
    0.06
    Activations Density 0.015%

    No Known Activations