© 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. 57780
    Prev
    Next
    INDEX
    Explanations

    $

    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
    iff
    -0.07
    éĤ£åĦ¿
    -0.07
    åĵī
    -0.07
     kla
    -0.07
    ilk
    -0.06
    ail
    -0.06
    é¡»
    -0.06
     spur
    -0.06
     rutina
    -0.06
    åĸ½
    -0.06
    POSITIVE LOGITS
    igare
    0.08
    åĻĮ
    0.08
    tesis
    0.07
    åĸĺæģ¯
    0.07
    å¤§éĽ¨
    0.07
    大åı¯
    0.06
    uwe
    0.06
    èĻĶ
    0.06
    olas
    0.06
    доÑģÑĤи
    0.06
    Activations Density 0.657%

    No Known Activations