© 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. 41959
    Prev
    Next
    INDEX
    Explanations

    ij academic journal articles

    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
    urar
    -0.08
    unken
    -0.08
    isky
    -0.07
    rey
    -0.07
     undes
    -0.07
    ikos
    -0.07
    ä¸İç»´ä¿®
    -0.07
    го
    -0.07
     Apel
    -0.06
    ijin
    -0.06
    POSITIVE LOGITS
    æĪijå°±è¦ģ
    0.08
    canf
    0.08
    erior
    0.08
    edly
    0.07
    ëŀĮ
    0.07
    vány
    0.07
    teis
    0.07
    ramid
    0.07
    ä¹IJä¸ļ
    0.07
    äºijå³°
    0.07
    Activations Density 0.026%

    No Known Activations