© 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. 18357
    Prev
    Next
    INDEX
    Explanations

    many some most cases contexts

    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
    umblr
    -0.07
    اÙħØ©
    -0.07
    å°½æĶ¶
    -0.07
    zÄĻd
    -0.07
    rovers
    -0.07
    itektur
    -0.07
    iggins
    -0.07
    моÑģков
    -0.07
    owards
    -0.07
    اذ
    -0.06
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.09
     circumstances
    0.08
    æĥħå½¢
    0.08
     cases
    0.08
    ï¼ĮãĢĬ
    0.08
     entanto
    0.07
    åł´åIJĪ
    0.07
     ÑģлÑĥÑĩаÑı
    0.07
     contexts
    0.07
     ocasiones
    0.07
    Activations Density 0.134%

    No Known Activations