© 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. 1898
    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
    åĴĮå½±åĵį
    -0.08
    å¿ĥæĢ¥
    -0.07
    oid
    -0.07
     slowing
    -0.07
    oidal
    -0.06
    .result
    -0.06
     result
    -0.06
    骡
    -0.06
    éĺ³åİ¿
    -0.06
     slow
    -0.06
    POSITIVE LOGITS
    hto
    0.08
    nger
    0.08
    etem
    0.07
    ä¸ŃåĽ½å®¶
    0.07
    çIJĨ
    0.07
    æĬ±è´Ł
    0.07
    iskon
    0.07
    åĨĬ
    0.07
    unittest
    0.07
    deaux
    0.07
    Activations Density 0.000%

    No Known Activations