© 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. 8004
    Prev
    Next
    INDEX
    Explanations

    project, drives, waiting, expect, work, crazy

    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
    ï¼İ
    -0.06
     ordinarily
    -0.06
    èĦ
    -0.06
     bens
    -0.06
    å®
    -0.06
    åħĥ
    -0.06
     duly
    -0.06
    åħ
    -0.06
    çŃ
    -0.06
    ä¾ĭå¦Ĥ
    -0.06
    POSITIVE LOGITS
    дзе
    0.08
    립
    0.08
    å±Ĩ
    0.08
    usen
    0.08
    ingan
    0.08
    ÑĨенÑĤ
    0.08
    ÚĺÙĩ
    0.08
    umen
    0.08
    petto
    0.08
    让æĪijçļĦ
    0.08
    Activations Density 0.002%

    No Known Activations