© 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. 63062
    Prev
    Next
    INDEX
    Explanations

    alphabetical, sexual, terminal, metal, accept, oxy

    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
     âĤ¬.
    -0.08
    istan
    -0.08
    imeo
    -0.08
    è¿Ļæł·çļĦä¸Ģ个
    -0.07
    otion
    -0.07
    stra
    -0.07
    blad
    -0.07
    ("");
    -0.07
    ä»ĸ们éľĢè¦ģ
    -0.07
    oque
    -0.07
    POSITIVE LOGITS
     namely
    0.10
    ï¼Łï¼ī
    0.09
    ?),
    0.07
    LOTS
    0.07
    -tabs
    0.07
     ...)
    0.06
    logs
    0.06
     <--
    0.06
    æľīåħ³è§Ħå®ļ
    0.06
    ),
    0.06
    Activations Density 0.204%

    No Known Activations