© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33065
    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
    åĬłæĭ¿å¤§
    -0.08
    áĭį
    -0.08
     mand
    -0.07
    chw
    -0.07
     Carta
    -0.07
     empl
    -0.07
    ä»ĸ认为
    -0.07
     Mandiri
    -0.07
    azar
    -0.07
    cosa
    -0.07
    POSITIVE LOGITS
    ermo
    0.07
    assis
    0.07
    çī¹æľĹ
    0.07
    æѦåĪĻ
    0.06
    HEADER
    0.06
    destination
    0.06
    éĸ
    0.06
    åıĸçļĦ
    0.06
    人æĪĸ
    0.06
    лаÑģ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.