© 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. 14281
    Prev
    Next
    INDEX
    Explanations

    vector fields

    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
    ##_
    -0.07
    æ¯Ķ以å¾Ģ
    -0.07
    æ¯Ķ以åīį
    -0.06
    èĨĬ
    -0.06
    ropp
    -0.06
    æĺ¥èī²
    -0.06
    ÙĬزة
    -0.06
    (^
    -0.06
    èĨĢ
    -0.06
     heavyweight
    -0.06
    POSITIVE LOGITS
    çļĦæĸ¹åIJij
    0.12
     vector
    0.11
     vectors
    0.10
    çŁ¢éĩı
    0.10
     directions
    0.10
    Vectors
    0.09
    åIJijéĩı
    0.09
    vector
    0.09
     Directions
    0.09
     Vector
    0.09
    Activations Density 0.007%

    No Known Activations