© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63908
    Prev
    Next
    INDEX
    Explanations

    output shaft

    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
    uo
    -0.06
    urun
    -0.06
    为ä¸Ģ个
    -0.06
    æĩ¸
    -0.06
    è¾¾
    -0.06
    è¡¡
    -0.06
    å¦ĤæŀľæĬĬ
    -0.06
    à¹Ģสริ
    -0.06
    FORM
    -0.06
    èĢĮæĪIJçļĦ
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºè¿ĻäºĽ
    0.09
    åľ°ä¹ħ
    0.09
    .cf
    0.09
    åĽłä¸ºæĺ¯
    0.08
    /Gate
    0.08
    ä¹Łå°±æĦıåij³çĿĢ
    0.08
    stime
    0.08
    ecause
    0.08
    emoc
    0.08
    Ñĥб
    0.08
    Activations Density 0.028%

    No Known Activations