© 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. 10175
    Prev
    Next
    INDEX
    Explanations

    `apple` followed by comma

    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
    quip
    -0.07
    ableObject
    -0.07
    eker
    -0.06
    robat
    -0.06
    å¼ĢåºĹ
    -0.06
     Holt
    -0.06
    (TM
    -0.06
    æĪijè§īå¾Ĺ
    -0.06
    ä¸Ģè§ī
    -0.06
     ($(
    -0.06
    POSITIVE LOGITS
     efficac
    0.08
    æľ¬æĸĩæĿ¥èĩª
    0.08
    åī©ä½ĻçļĦ
    0.07
    æĸĩçIJĨ
    0.07
    otos
    0.07
    é¤ĺ
    0.07
     Torrent
    0.07
    -pad
    0.07
    LEMENT
    0.06
    åī©
    0.06
    Activations Density 0.045%

    No Known Activations