© 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. 43269
    Prev
    Next
    INDEX
    Explanations

    function $f : \mathbb R \to \mathbb R$

    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
    æĹłèĻij
    -0.07
    累累
    -0.07
    ç½ĹåĪĹ
    -0.07
    hr
    -0.07
     Pilk
    -0.07
    èģĶå¸Ń
    -0.07
    .ua
    -0.07
    æĺİçģ«
    -0.07
    天çªĹ
    -0.06
    Insensitive
    -0.06
    POSITIVE LOGITS
    -wide
    0.08
    /maps
    0.07
    èµ´
    0.07
    ibera
    0.07
    Maps
    0.07
     maps
    0.07
    åįĴ
    0.07
    çļĦ对象
    0.07
    /output
    0.07
    è¿Ķ
    0.07
    Activations Density 0.025%

    No Known Activations