© 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. 16440
    Prev
    Next
    INDEX
    Explanations

    condition variables and locks

    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
    åįľ
    -0.08
     footnote
    -0.07
    agan
    -0.07
    ç¬ĶçĶ»
    -0.07
    æµ·éģĵ
    -0.06
    èĦļ趾
    -0.06
    abwe
    -0.06
    åĮħåĽ´
    -0.06
     evaluated
    -0.06
    ilm
    -0.06
    POSITIVE LOGITS
    .signal
    0.09
    колÑĮ
    0.08
    .Signal
    0.08
    essaging
    0.08
     mutual
    0.08
     заÑĩа
    0.08
    _named
    0.07
    (named
    0.07
    ุà¹Īม
    0.07
    -publish
    0.07
    Activations Density 0.079%

    No Known Activations