© 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. 8710
    Prev
    Next
    INDEX
    Explanations

    convenience and convenience

    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
    pear
    -0.09
    Ñļи
    -0.09
    orean
    -0.08
    ondi
    -0.08
    orea
    -0.08
    ènes
    -0.08
    æĺ¯ä¸įæĺ¯å¾Ī
    -0.08
    .manual
    -0.07
    ãģ¡ãĤĥãĤĵãģ¨
    -0.07
    大çģ«
    -0.07
    POSITIVE LOGITS
    èµ·è§ģ
    0.13
    ly
    0.09
    æĸ¹ä¾¿çļĦ
    0.09
    liness
    0.09
    est
    0.09
    æĸ¹ä¾¿
    0.09
    æľīåĬł
    0.09
    便åĪ©
    0.08
    สà¸ļาย
    0.08
    æŀģäºĨ
    0.08
    Activations Density 0.051%

    No Known Activations