© 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. 34742
    Prev
    Next
    INDEX
    Explanations

    .logging

    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
    丰èĥ¸
    -0.08
    ä¼ĺæĥłä»·
    -0.08
    è¿ľæľŁ
    -0.08
    encv
    -0.07
    æµģåĪ©
    -0.07
     Certificate
    -0.07
     circumcision
    -0.07
    ideshow
    -0.07
    ullah
    -0.07
    ertools
    -0.07
    POSITIVE LOGITS
    entrale
    0.07
    Filter
    0.07
    ثر
    0.07
    åĦĴ
    0.06
    .logging
    0.06
    éª
    0.06
     lap
    0.06
     recording
    0.06
     logging
    0.06
    çī¹å°Ķ
    0.06
    Activations Density 0.238%

    No Known Activations