© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    max value limits

    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
    ofil
    -0.07
    .basename
    -0.07
    leck
    -0.07
    é¡¹çĽ®æī¿åĬŀåįķä½į
    -0.06
     gob
    -0.06
    anche
    -0.06
    ¬ģ
    -0.06
    aner
    -0.06
    讳
    -0.06
     поÑģлед
    -0.06
    POSITIVE LOGITS
    abay
    0.08
    缩å°ı
    0.08
    ä¸Ĭ好
    0.07
    缩åĩı
    0.07
     guessing
    0.07
    縮
    0.07
    åı¯è¡Į
    0.07
     suspects
    0.07
    /source
    0.07
    ière
    0.07
    Activations Density 0.003%

    No Known Activations