© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29848
    Prev
    Next
    INDEX
    Explanations

    see

    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
    æĬ¥è®°èĢħ
    -0.09
    aveur
    -0.09
    -cols
    -0.09
    indow
    -0.09
    åĽ¢æĪIJåijĺ
    -0.09
    åĪĨä¹ĭä¸Ģ
    -0.09
    ecal
    -0.09
    малÑĮ
    -0.09
    arder
    -0.09
    caffold
    -0.09
    POSITIVE LOGITS
    see
    0.09
    Âł
    0.08
    1
    0.08
    See
    0.07
    3
    0.07
     see
    0.07
    0.07
    缸åºĶçļĦ
    0.07
    (
    0.07
    7
    0.07
    Activations Density 0.467%

    No Known Activations