© 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. 65123
    Prev
    Next
    INDEX
    Explanations

    integral polytope

    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
    ä¸Ģæī«
    -0.08
    idot
    -0.08
    cks
    -0.07
    ÙĦاÙĦ
    -0.07
    wers
    -0.07
    ->__
    -0.07
    é²²
    -0.07
    ulp
    -0.07
    ubb
    -0.07
    为åŃ¦æł¡
    -0.07
    POSITIVE LOGITS
    åŀĭ
    0.08
    æĺ¯æĮĩ
    0.08
    ness
    0.08
    å°±æĺ¯è¯´
    0.07
    /non
    0.07
    åIJįåī¯åħ¶å®ŀ
    0.07
     بÙĪدÙĨ
    0.07
     demais
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    æĦıåij³
    0.07
    Activations Density 0.041%

    No Known Activations