© 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. 17103
    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
    ulum
    -0.08
    brig
    -0.07
    çĶļèĩ³æĺ¯
    -0.06
    åŀĭ
    -0.06
    ÑıÑĤи
    -0.06
    usel
    -0.06
    æĪĸèĢħæĺ¯
    -0.06
    çĤ¹æ»´
    -0.06
    æ»´
    -0.06
    çĦ¶åIJİæĺ¯
    -0.06
    POSITIVE LOGITS
    ozn
    0.08
    iblio
    0.08
    aurant
    0.07
    ä¹ĿäºĶ
    0.07
    禺
    0.07
     Altro
    0.07
    åį³æĹ¥èµ·èĩ³
    0.07
    TagName
    0.07
    oitu
    0.07
    éĩĮåħĭ
    0.07
    Activations Density 0.000%

    No Known Activations