© 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. 21733
    Prev
    Next
    INDEX
    Explanations

    commas separating items in lists or sequences of numbers and variables.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    æīĢè°ĵ
    -0.07
    ä¸ĵ为
    -0.07
    ç¼ĺæķħ
    -0.07
     âĢ¦
    -0.07
     ...
    -0.07
    åħ¥åı£
    -0.07
    è¿Ļç±»
    -0.06
    åIJĦç±»
    -0.06
    efs
    -0.06
    arrow
    -0.06
    POSITIVE LOGITS
    Compat
    0.08
    ATAN
    0.08
    ãĥ¼ãĥģ
    0.08
    wirt
    0.07
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.07
    槻
    0.07
    ."]
    0.07
    unen
    0.07
    ä¸īå°º
    0.07
    ihn
    0.07
    Activations Density 0.000%

    No Known Activations