© 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. 65204
    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
    ı
    -0.07
    almaz
    -0.06
    ertime
    -0.06
    峨
    -0.06
    èıģ
    -0.06
    [pos
    -0.06
     illet
    -0.06
    表示æĦŁè°¢
    -0.06
    æµİ
    -0.06
    ãģĹãĤĥ
    -0.06
    POSITIVE LOGITS
    è¿Ļéĥ¨
    0.08
    ÑĤол
    0.07
    poon
    0.07
    ì°©
    0.07
    _CTRL
    0.07
    ignum
    0.07
    æ¯Ķå¦Ĥ
    0.07
    deen
    0.07
    ãĢĭï¼Į
    0.06
    ungeon
    0.06
    Activations Density 0.000%

    No Known Activations