© 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. 46512
    Prev
    Next
    INDEX
    Explanations

    need for OPT extension

    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
    éľĢè¦ģ注æĦıçļĦæĺ¯
    -0.08
    åºĶæī¿æĭħ
    -0.08
    éľĢè¦ģ注æĦı
    -0.08
    éľĢ注æĦı
    -0.07
    åºĶå½ĵæī¿æĭħ
    -0.07
    ))]
    -0.07
    æĥ³åĪ°çļĦ
    -0.07
    人æīĢ
    -0.07
    éľĢè¦ģèĢĥèĻij
    -0.07
    æ·±åıĹ广大
    -0.07
    POSITIVE LOGITS
     urgently
    0.11
     ÑĩÑĤобÑĭ
    0.11
    æŶéĹ´æĿ¥
    0.10
     möglichst
    0.09
     dringend
    0.09
    æīįèĥ½æľī
    0.09
    æĿ¥å®ĮæĪIJ
    0.09
     unbedingt
    0.09
     Ñīоб
    0.09
    ä»ĸæĿ¥
    0.09
    Activations Density 0.298%

    No Known Activations