© 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. 46438
    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
    顾åIJįæĢĿ
    -0.08
    æĺĵè´Ń
    -0.07
    aire
    -0.07
    æĥĭ
    -0.07
     кое
    -0.07
     Wester
    -0.07
    姨å¦Ī
    -0.07
    åĪĩå®ŀæĬĬ
    -0.07
    empat
    -0.07
     Wolfe
    -0.07
    POSITIVE LOGITS
    çŀĴ
    0.07
    Ïģε
    0.07
     asn
    0.06
     threads
    0.06
     Communic
    0.06
    _RS
    0.06
     ger
    0.06
    vaart
    0.06
    _REQUIRE
    0.06
    并对åħ¶
    0.06
    Activations Density 0.000%

    No Known Activations