© 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. 24207
    Prev
    Next
    INDEX
    Explanations

    Hogwarts Potter characters

    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
    าà¸ĩ
    -0.07
     bib
    -0.06
    omi
    -0.06
    çķĻä½ı
    -0.06
    ัà¸ķ
    -0.06
     stat
    -0.06
    رÙĪÛĮ
    -0.06
     linker
    -0.06
    ([...
    -0.06
    åijĤ
    -0.06
    POSITIVE LOGITS
    éķ¿æ²Ļ
    0.08
     Wolfs
    0.08
    asley
    0.08
     Hogwarts
    0.07
    ç»ıåħ¸
    0.07
    å·«å¸Ī
    0.07
    æ²¢
    0.07
     vĩ
    0.07
    è£ĺ
    0.07
    uckland
    0.07
    Activations Density 0.093%

    No Known Activations