© 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. 51933
    Prev
    Next
    INDEX
    Explanations

    ip ranges and subnetting

    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
    ationally
    -0.08
    iseau
    -0.08
    mium
    -0.08
     leo
    -0.08
    imately
    -0.07
    Occurred
    -0.07
     vok
    -0.07
    (Function
    -0.07
    лове
    -0.07
    cini
    -0.07
    POSITIVE LOGITS
    åĪĴåĪĨ
    0.08
     granularity
    0.08
    æİ©
    0.07
     administr
    0.07
     extent
    0.07
    mask
    0.07
     administered
    0.06
    ç²Ĵ度
    0.06
    rite
    0.06
     precision
    0.06
    Activations Density 0.004%

    No Known Activations