© 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. 30052
    Prev
    Next
    INDEX
    Explanations

    unicode, sic, misspelled words

    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
    åIJĦæľīåIJĦ
    -0.08
    inne
    -0.08
    vo
    -0.07
     indirectly
    -0.07
    essen
    -0.07
    è¿Ļæł·çļĦè¯Ŀ
    -0.07
    éĥ½ä¸įè¦ģ
    -0.07
    éĹ´æİ¥
    -0.07
    éģ¥éģ¥
    -0.07
    并ä¸įé«ĺ
    -0.07
    POSITIVE LOGITS
     spelling
    0.09
     typo
    0.09
    諧
    0.08
    สะ
    0.08
    èħĶ
    0.08
    åħĭæľįäºĨ
    0.07
    sic
    0.07
     spelled
    0.07
    unicode
    0.07
    åħĭæľį
    0.07
    Activations Density 0.047%

    No Known Activations