© 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. 18890
    Prev
    Next
    INDEX
    Explanations

    exponent and power laws

    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
    вок
    -0.08
    -online
    -0.08
    INTERNAL
    -0.07
    èµĤ
    -0.07
    ADDING
    -0.07
    aldi
    -0.07
     fornitori
    -0.07
    ecam
    -0.07
    hdl
    -0.07
    ekh
    -0.07
    POSITIVE LOGITS
     exponent
    0.15
    æĮĩæķ°
    0.11
     expo
    0.09
    å¹Ĥ
    0.08
     power
    0.08
    å·
    0.08
    å¾ĭ
    0.08
    æĭĽ
    0.08
     powers
    0.07
    æĿĥåĬĽ
    0.07
    Activations Density 0.117%

    No Known Activations