© 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. 61573
    Prev
    Next
    INDEX
    Explanations

    math, science, and logic

    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
    丼
    -0.08
    reff
    -0.08
    ansa
    -0.07
     redesigned
    -0.07
    èĪ
    -0.07
    akis
    -0.07
    coma
    -0.07
    è´±
    -0.07
    esign
    -0.07
    æİ¥
    -0.07
    POSITIVE LOGITS
     contentious
    0.07
     philosophical
    0.07
    çŃīä»·
    0.07
    å¤ŁçĶ¨
    0.07
    azon
    0.06
     fiat
    0.06
     philosophers
    0.06
    ufficient
    0.06
    æĬĹæű
    0.06
    ós
    0.06
    Activations Density 0.008%

    No Known Activations