© 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. 61387
    Prev
    Next
    INDEX
    Explanations

    res judicata

    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
    pto
    -0.09
    /GPL
    -0.08
    æĮ¤
    -0.08
    æĭ¥æĮ¤
    -0.07
     writable
    -0.07
    å·§
    -0.07
    ç±»çŃī
    -0.07
    åĪļ好
    -0.07
    èĩªçĦ¶èĢĮ
    -0.07
    æģ°å¥½
    -0.07
    POSITIVE LOGITS
    ä¸įè¦ģè½»æĺĵ
    0.10
     barring
    0.09
    éĻ¤éĿŀ
    0.09
    ä¸Ģç»ı
    0.09
     unless
    0.09
    ä¸ĢæŦ
    0.08
    å°Ĭéĩį
    0.08
     sealed
    0.08
    ä¿¡èµĸ
    0.08
    ç»´æĬ¤
    0.08
    Activations Density 0.052%

    No Known Activations