© 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. 20972
    Prev
    Next
    INDEX
    Explanations

    health systems efforts

    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
     (::
    -0.08
    çļĦç»ıèIJ¥çIJĨ念
    -0.07
    etri
    -0.07
    SHOT
    -0.07
    å°½åľ¨
    -0.06
    okable
    -0.06
    åĭĭ
    -0.06
    ÑĢÑĥжи
    -0.06
    æ¸ħæ²³
    -0.06
    ÅĪa
    -0.06
    POSITIVE LOGITS
     btw
    0.09
     übrigens
    0.09
    åĪ°è¿Ļ个
    0.08
     therefore
    0.07
    è¿Ļä¸ĢçĤ¹
    0.07
    anto
    0.07
     roma
    0.07
    árt
    0.07
    åĽłæѤ
    0.07
     geni
    0.07
    Activations Density 1.666%

    No Known Activations