© 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. 62583
    Prev
    Next
    INDEX
    Explanations

    .com followed by is

    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
    aram
    -0.07
    assis
    -0.07
    ç²±
    -0.07
    bound
    -0.07
    iasi
    -0.06
    รà¹Īวà¸ĩ
    -0.06
     Carrier
    -0.06
    edad
    -0.06
    享年
    -0.06
    ব
    -0.06
    POSITIVE LOGITS
    éĤ£ç§į
    0.08
    apons
    0.08
    apore
    0.07
    arei
    0.07
    éĤ£ç¨®
    0.07
    -trade
    0.07
    anker
    0.07
     nød
    0.07
    apper
    0.07
    交æį¢
    0.07
    Activations Density 0.001%

    No Known Activations