© 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. 56259
    Prev
    Next
    INDEX
    Explanations

    file extensions or names

    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
    .yy
    -0.07
    éŀĺ
    -0.07
    \L
    -0.07
    åIJĮåľ¨
    -0.07
    å°ıçıŃ
    -0.07
    bes
    -0.06
    utive
    -0.06
    ]|
    -0.06
    uyo
    -0.06
    循
    -0.06
    POSITIVE LOGITS
    annes
    0.08
    elivery
    0.07
    .pb
    0.07
    为ä»Ģä¹Īä¼ļ
    0.07
    佩
    0.07
    èIJ¨å°Ķ
    0.07
    epy
    0.06
     плÑİÑģ
    0.06
    åIJīå®ī
    0.06
    åįģéĩĮ
    0.06
    Activations Density 0.272%

    No Known Activations