© 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. 13920
    Prev
    Next
    INDEX
    Explanations

    so what

    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
    utage
    -0.10
    libc
    -0.09
    åIJij被åijĬ
    -0.09
    edly
    -0.09
     Festiv
    -0.09
    quement
    -0.08
    ewel
    -0.08
    reté
    -0.08
    venture
    -0.08
    åĵī
    -0.08
    POSITIVE LOGITS
     silly
    0.06
    æ·ĩ
    0.06
     done
    0.06
    ä¸įä»İ
    0.06
    å¦Ĥæŀľä½łæľī
    0.06
    éĿŀ常æĸ¹ä¾¿
    0.06
     arguing
    0.06
    äºĨ
    0.06
    å¦Ĥæŀľæĺ¯
    0.06
    </think>
    0.05
    Activations Density 0.013%

    No Known Activations