© 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. 19730
    Prev
    Next
    INDEX
    Explanations

    code execution context

    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
    uff
    -0.08
    ä½Ĩæĺ¯å®ĥ
    -0.07
    ousy
    -0.07
    认è¯ĨåĪ°äºĨ
    -0.06
    inte
    -0.06
    iph
    -0.06
     "*",
    -0.06
    ä¸ĢæĶ¹
    -0.06
     "=",
    -0.06
    uru
    -0.06
    POSITIVE LOGITS
    athed
    0.07
    kert
    0.07
    ãģĨãģ¡ãģ«
    0.07
    arina
    0.07
     fwrite
    0.07
    _acquire
    0.07
    ><![
    0.07
     setattr
    0.07
    apper
    0.06
     diser
    0.06
    Activations Density 0.168%

    No Known Activations