© 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. 56934
    Prev
    Next
    INDEX
    Explanations

    probability distribution and weights

    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
    磫
    -0.08
    æĹłæķ°
    -0.07
    Ñĥдо
    -0.07
    举ä¸ĸ
    -0.07
     ìŀĦ
    -0.07
    çŁ¯
    -0.07
    pon
    -0.07
    serter
    -0.07
    à¸ķà¹ī
    -0.07
    ubr
    -0.07
    POSITIVE LOGITS
     weights
    0.13
    weights
    0.13
    æĿĥéĩį
    0.11
    Weights
    0.10
    weight
    0.10
     probabilities
    0.10
     weighting
    0.10
    -weight
    0.09
     weight
    0.09
    distribution
    0.09
    Activations Density 0.011%

    No Known Activations