© 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. 12558
    Prev
    Next
    INDEX
    Explanations

    mesh size

    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
    _lengths
    -0.09
    éķ¿åº¦ä¸º
    -0.08
     Length
    -0.08
     length
    -0.08
    å¾Īéķ¿
    -0.07
    è¾ĥéķ¿çļĦ
    -0.07
    Length
    -0.07
     panjang
    -0.07
    è¾ĥéķ¿
    -0.07
     lengths
    -0.07
    POSITIVE LOGITS
    å¯Ĩ度
    0.11
    é¢ijçİĩ
    0.10
    å¯ĨéĽĨ
    0.10
     Wolff
    0.09
    rate
    0.09
    rates
    0.09
     density
    0.09
     densities
    0.09
     rates
    0.09
    _rate
    0.09
    Activations Density 0.026%

    No Known Activations