© 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. 29544
    Prev
    Next
    INDEX
    Explanations

    maybe you should

    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
    èĩ³å°ij
    -0.07
    ç²Ĺ
    -0.06
    å¤ĩ
    -0.06
    æľĢå°ij
    -0.06
     hopefully
    -0.06
    å°ī
    -0.06
     («
    -0.06
    ihan
    -0.06
    icios
    -0.06
    æݨå¼Ģ
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.12
    èİ«è¿ĩäºİ
    0.09
     something
    0.08
    åħ³æ³¨åħ¬ä¼Ĺåı·
    0.08
    æĬķèµĦæĪĸ
    0.08
    tz
    0.08
    çļĦè¿ĺæľī
    0.08
    æ¯Ķå¦Ĥ
    0.07
    åĮºéķ¿
    0.07
     roli
    0.07
    Activations Density 0.077%

    No Known Activations