© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58825
    Prev
    Next
    INDEX
    Explanations

    measurement, observation, application

    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
    波士
    -0.07
    gau
    -0.07
    aup
    -0.07
    azi
    -0.07
    odox
    -0.07
    é¢Ĭ
    -0.07
    dap
    -0.07
    chor
    -0.07
    为ä»Ģä¹Īä¸į
    -0.07
    éĿ¡
    -0.06
    POSITIVE LOGITS
     predictable
    0.09
     efectiv
    0.07
     measurable
    0.07
     tercatat
    0.07
     observable
    0.07
    æĹłå½±
    0.07
    èĩ´
    0.07
    é¢Ħç¥Ŀ
    0.07
     reflected
    0.07
     sampled
    0.06
    Activations Density 0.205%

    No Known Activations