© 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. 39039
    Prev
    Next
    INDEX
    Explanations

    connected simply connected

    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
    ç½²
    -0.07
     Zah
    -0.07
    éļĶ
    -0.07
     sprayed
    -0.06
     spread
    -0.06
    azah
    -0.06
    Ĥ¬
    -0.06
     zet
    -0.06
    üll
    -0.06
    åĸ·æ´Ĵ
    -0.06
    POSITIVE LOGITS
    irma
    0.09
    幡
    0.08
    ardu
    0.08
    AHA
    0.08
     loops
    0.08
    loops
    0.08
    ç»ķ
    0.08
    باÙĨ
    0.08
    æĩ
    0.08
    LOOP
    0.07
    Activations Density 0.004%

    No Known Activations