© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    damage and loss

    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
     mier
    -0.08
    å®īåħ¨æ£ĢæŁ¥
    -0.07
    æľīäºĽä¸į
    -0.07
    áī°
    -0.07
    ALLOC
    -0.07
    çijķ
    -0.07
    Else
    -0.07
    chol
    -0.07
    alai
    -0.07
    Palette
    -0.07
    POSITIVE LOGITS
    累积
    0.10
    ä¸Ģ寸
    0.10
    åĬłéĢŁ
    0.10
     dần
    0.09
    积累çļĦ
    0.09
    积累
    0.09
    æ¶Ī磨
    0.09
     Accum
    0.09
    æľĢå¿«çļĦ
    0.09
    æĹ¥æ¸IJ
    0.09
    Activations Density 0.131%

    No Known Activations