© 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. 56755
    Prev
    Next
    INDEX
    Explanations

    airlineprader-willis syndrome

    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
    èĢIJ
    -0.08
    erbe
    -0.07
    ontro
    -0.07
    Ñĸд
    -0.07
     termin
    -0.07
    ocat
    -0.07
    个æľĪåIJİ
    -0.07
    erlo
    -0.06
    vre
    -0.06
    å¾·
    -0.06
    POSITIVE LOGITS
    çļĦä¸Ģ项éĩįè¦ģ
    0.08
    æ»ļ
    0.07
    rapper
    0.07
    éĻ¤äºĨæľī
    0.07
    Å¡Äį
    0.07
    speech
    0.07
    ses
    0.07
    iras
    0.07
    æĸ°äº¬
    0.07
     помимо
    0.07
    Activations Density 0.973%

    No Known Activations