© 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. 10999
    Prev
    Next
    INDEX
    Explanations

    partial x=\frac{d f}{d p}

    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
    δÏĮ
    -0.08
    è¿Ļç§įæĦŁè§ī
    -0.08
     ([[
    -0.08
    ={({
    -0.08
    çļĦ梦
    -0.07
    ewood
    -0.07
    ä¸ŃçļĦæķ°æį®
    -0.07
    alani
    -0.07
    åı¯æ¢¦
    -0.07
    polis
    -0.07
    POSITIVE LOGITS
    tor
    0.07
    ืà¸Ń
    0.06
    olg
    0.06
    emy
    0.06
     skr
    0.06
    ensch
    0.06
    èĢģèĢģå®ŀ
    0.06
    天主
    0.06
    æŧ
    0.06
    ä¸ĩä¸Ī
    0.06
    Activations Density 0.002%

    No Known Activations