© 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. 47423
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    колÑĮ
    -0.08
    çķħ
    -0.07
    åĶ§
    -0.07
    梳
    -0.07
     ám
    -0.06
    æĿ¥å¾Ģ
    -0.06
    stre
    -0.06
    è¡¥
    -0.06
    برÛĮ
    -0.06
    ore
    -0.06
    POSITIVE LOGITS
    irti
    0.07
    ç«ĭåĬŁ
    0.07
    rze
    0.07
    å¤ļ天
    0.07
    irt
    0.07
    _construct
    0.07
     irré
    0.07
    ÑĢазÑĥ
    0.07
    annis
    0.07
    estone
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.