© 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. 60280
    Prev
    Next
    INDEX
    Explanations

    automata, replacement, promote, more

    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¸įæĪIJ
    -0.08
     portale
    -0.08
    产åĵģä¸Ńå¿ĥ
    -0.07
    à·ĥà·Ĭ
    -0.07
    ört
    -0.07
    æĵ
    -0.07
    önt
    -0.07
    åľ¨åŁºå±Ĥ
    -0.07
    æĴ¬
    -0.07
    spur
    -0.07
    POSITIVE LOGITS
     Turing
    0.09
    åIJIJ
    0.07
    oper
    0.07
     Laurent
    0.07
     emulator
    0.07
    .state
    0.07
     coloring
    0.07
    æľºèĥ½
    0.07
    à¹Ģà¸Ħรืà¹Īà¸Ńà¸ĩ
    0.07
    oger
    0.06
    Activations Density 0.025%

    No Known Activations