© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    other things

    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
    èĢĮä¸įæĺ¯
    -0.08
     Either
    -0.07
     instead
    -0.07
    oord
    -0.07
     either
    -0.07
     rather
    -0.07
    orz
    -0.07
    åĬ¿
    -0.06
    é£
    -0.06
    祺
    -0.06
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.10
    è¿ĺæľīåĵªäºĽ
    0.09
    åı¯èĥ½åŃĺåľ¨
    0.09
    éļIJåĮ¿
    0.09
    åħ¶ä»ĸ
    0.08
    鼶æĺŁ
    0.08
    çļĦè¿ĺæľī
    0.08
     egyéb
    0.08
    è¿ĺæľīåħ¶ä»ĸ
    0.08
     nữa
    0.08
    Activations Density 0.008%

    No Known Activations