© 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. 2649
    Prev
    Next
    INDEX
    Explanations

    farm related content

    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
    ç«ĭåľ¨
    -0.09
    åľ¨è¿ĻåĦ¿
    -0.08
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    åħ¶åľ¨
    -0.08
    åľ¨åIJİéĿ¢
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    åľ¨æѤ
    -0.08
     darin
    -0.08
    åľ¨è¿ĻéĩĮ
    -0.07
    å®ĥåľ¨
    -0.07
    POSITIVE LOGITS
     angekommen
    0.12
    çī¹åĪ«æĺ¯åľ¨
    0.10
    åijĨäºĨ
    0.09
     befind
    0.08
    lama
    0.08
     ×ķ×ij
    0.08
    ì¡°ì°¨
    0.08
     rè
    0.08
    çļĦæīĢæľī
    0.08
    åıijçĶŁçļĦäºĭæĥħ
    0.08
    Activations Density 0.313%

    No Known Activations