© 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. 61596
    Prev
    Next
    INDEX
    Explanations

    Kelley William Treasurer

    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
    agh
    -0.08
    aja
    -0.08
    å±ŀå®ŀ
    -0.07
     ÂŃ
    -0.07
    akon
    -0.07
    enzie
    -0.07
    egative
    -0.06
    itori
    -0.06
    æĪIJ绩
    -0.06
    ÏģÏį
    -0.06
    POSITIVE LOGITS
    olley
    0.08
    CEED
    0.07
    osto
    0.07
    fil
    0.06
    ulte
    0.06
    kdir
    0.06
    ิà¸ķิ
    0.06
    ãģłãĤī
    0.06
    isson
    0.06
    .mit
    0.06
    Activations Density 0.025%

    No Known Activations