© 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. 22606
    Prev
    Next
    INDEX
    Explanations

    with specific examples

    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
    ä¹Łå¾Īéĩįè¦ģ
    -0.07
    skar
    -0.07
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    -0.07
    å°±å°Ĩ
    -0.07
    å°±æľīäºĨ
    -0.07
    å°±éĿŀ常
    -0.07
    追æ±Ĥåįĵè¶Ĭ
    -0.07
    æīįçŁ¥éģĵ
    -0.07
    åľ¨ä¸Ģèµ·
    -0.07
    EEDED
    -0.07
    POSITIVE LOGITS
     notable
    0.09
     emphasis
    0.08
     exceptions
    0.08
     Ausnahme
    0.08
    主è¦ģéĽĨä¸Ńåľ¨
    0.08
     notably
    0.08
    æĿ¥è¶Ĭ
    0.07
    æ¯ı个
    0.07
    ym
    0.07
     exception
    0.07
    Activations Density 0.255%

    No Known Activations