© 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. 18077
    Prev
    Next
    INDEX
    Explanations

    special issue, exception, features, events

    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
    inous
    -0.09
    rary
    -0.09
    ÏĢοÏĦε
    -0.09
    å¡ĺ
    -0.09
    geois
    -0.08
    bersome
    -0.08
    ISIBLE
    -0.08
    ehold
    -0.08
    laves
    -0.08
    ancy
    -0.08
    POSITIVE LOGITS
    -purpose
    0.11
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    0.10
    ity
    0.09
    ÃŃsimo
    0.09
    izing
    0.08
    ized
    0.08
    issimo
    0.08
    zed
    0.08
    çī¹æ®Ĭ
    0.08
    cial
    0.08
    Activations Density 0.046%

    No Known Activations