© 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. 64605
    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¦but
    -0.08
    æľī没æľī
    -0.08
     nowadays
    -0.08
     âĢ¦.
    -0.08
    æĺ¯ä¸įæĺ¯
    -0.08
     maybe
    -0.08
    egger
    -0.07
    æĺ¯åIJ¦æŃ£ç¡®
    -0.07
    çĥŃçĪ±çĶŁæ´»
    -0.07
     ðŁĻĤ
    -0.07
    POSITIVE LOGITS
    ä¸Ĭåįĩèĩ³
    0.07
    $(
    0.07
    .Interop
    0.06
    第ä¸Ģ人
    0.06
    packing
    0.06
    $\
    0.06
    $_
    0.06
    ä¸į失
    0.06
     $(
    0.06
     contr
    0.06
    Activations Density 0.000%

    No Known Activations