© 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. 15097
    Prev
    Next
    INDEX
    Explanations

    polynomial equations

    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
    -0.06
    attan
    -0.06
     R
    -0.06
    walt
    -0.06
    Âł
    -0.06
    µ
    -0.06
    ร
    -0.05
     H
    -0.05
    丼
    -0.05
    仪åĻ¨è®¾å¤ĩ
    -0.05
    POSITIVE LOGITS
    جة
    0.09
    idla
    0.09
    شرة
    0.09
    ucid
    0.08
    sembler
    0.08
    ihat
    0.08
    uteur
    0.08
    Äħcz
    0.08
    hoto
    0.08
    yš
    0.07
    Activations Density 0.008%

    No Known Activations