© 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. 29004
    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
    _rat
    -0.08
    Ñĥз
    -0.08
    à¸Ńุ
    -0.07
     ÙĨÙĩ
    -0.07
    @\
    -0.06
    è§ģ表
    -0.06
    ä¸Ĭä¸ĭæĸĩ
    -0.06
     [\
    -0.06
     [].
    -0.06
    ilty
    -0.06
    POSITIVE LOGITS
     prest
    0.07
    lector
    0.07
    åIJĥåIJĥ
    0.07
    èĩªæĭħ
    0.07
    éĥ½èĥ½å¤Ł
    0.07
    èĥ½å¤ŁéĢļè¿ĩ
    0.07
    éĻĪå¿Ĺ
    0.07
    çļĦå·¥ä½ľæĢģ度
    0.06
    TA
    0.06
    å±¥
    0.06
    Activations Density 0.000%

    No Known Activations