© 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. 7702
    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
    âĢ¦
    -0.08
    *
    -0.07
    -0.06
    onic
    -0.06
    MG
    -0.06
    巨大
    -0.06
    ...
    -0.06
    éģ¨
    -0.06
    éĬ
    -0.06
    /
    -0.05
    POSITIVE LOGITS
    å¼ķ以为
    0.08
    lsru
    0.08
    ä¸Ģè¯ķ
    0.08
    æľ¬æĸĩ为åįļ主
    0.08
    çĻ¾å¿Ļ
    0.08
     '",
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    inten
    0.08
    -kit
    0.07
    åĽŀè¿ĩç¥ŀ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.