© 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. 63786
    Prev
    Next
    INDEX
    Explanations

    relationship, air, sided, blue, based, return

    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
    æ©
    -0.07
    schn
    -0.07
    uru
    -0.07
    ç¼¥
    -0.06
    æĹłæĥħ
    -0.06
    족
    -0.06
    软å®ŀåĬĽ
    -0.06
    åĺ¶
    -0.06
    acea
    -0.06
    ULD
    -0.06
    POSITIVE LOGITS
    å°±æĺ¯ä¸į
    0.09
    æĺ¯æĮĩåľ¨
    0.08
    æĪĸä¸į
    0.08
    主è¦ģæĺ¯æĮĩ
    0.08
    æĺ¯æĮĩ
    0.07
    çī¹çº¦
    0.07
    ä½Ĩæľī
    0.07
    å°±æĺ¯æĮĩ
    0.07
    ä¹Łåı«
    0.07
    iry
    0.07
    Activations Density 0.069%

    No Known Activations