© 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. 60675
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sök
    -0.07
    lepas
    -0.07
    ä»»åĩŃ
    -0.07
    à¸ļริ
    -0.06
    æĭ¯
    -0.06
    èĩªæѤ
    -0.06
    æĸ¹ä¾¿
    -0.06
    زÙĪÙĨ
    -0.06
    ä¸ŃæŃ¢
    -0.06
    éĥ½åIJĪ
    -0.06
    POSITIVE LOGITS
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    0.08
    ⾨
    0.07
    åĪĽéĢłä¸Ģ个
    0.07
    æĥ³å¾Ĺ
    0.07
    wai
    0.07
    æĥ³æĥ³
    0.07
     Schne
    0.07
    _flow
    0.07
    istas
    0.07
    _extend
    0.06
    Activations Density 0.000%

    No Known Activations