© 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. 31698
    Prev
    Next
    INDEX
    Explanations

    plan, concepts, events

    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
    ryp
    -0.07
    è¥
    -0.07
    âĢ¦).
    -0.07
    apk
    -0.07
    为ä»Ģä¹Ī说
    -0.07
    aspers
    -0.06
    னà¯įà®±à¯ģ
    -0.06
    æ²ĥæĸ¯
    -0.06
    ä¸Ńæµ·
    -0.06
    çİ°çĬ¶åıĬ
    -0.06
    POSITIVE LOGITS
    -serif
    0.07
    (("
    0.07
    å¾Īæĺİæĺ¾
    0.06
    æľŁçļĦ
    0.06
    gone
    0.06
    aisu
    0.06
    ä¸ĬæĿ¥çļĦ
    0.06
    .cwd
    0.06
    ÙĩÙIJ
    0.06
    ADVERTISEMENT
    0.06
    Activations Density 0.010%

    No Known Activations