© 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. 56156
    Prev
    Next
    INDEX
    Explanations

    AlxGa1-xN or AsxSe1-x

    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
     hinter
    -0.08
    onda
    -0.08
    à¹Ĥà¸ŀ
    -0.07
     Feedback
    -0.07
    .pipe
    -0.07
    andia
    -0.07
    è¿ľä½İäºİ
    -0.07
    ajt
    -0.07
    åįģæĿ¡
    -0.07
    .readyState
    -0.07
    POSITIVE LOGITS
    ´
    0.08
    ä½įç½®ä¸Ĭ
    0.07
    MaxLength
    0.07
    çļĦä½įç½®
    0.06
    elo
    0.06
    ivot
    0.06
    ubs
    0.06
    -Man
    0.06
    wikipedia
    0.06
     Allgeme
    0.06
    Activations Density 0.003%

    No Known Activations