© 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. 28766
    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
    aser
    -0.08
    wah
    -0.08
    aglio
    -0.08
    ÙĦÙĩ
    -0.08
    æĶ¹äºĨ
    -0.08
    GRA
    -0.07
    çļĭ
    -0.07
    á»ħu
    -0.07
    кÑĥпа
    -0.07
    авли
    -0.07
    POSITIVE LOGITS
    edor
    0.07
    ian
    0.06
    åľ¨ä¿Ŀè¯ģ
    0.06
    èµĸ
    0.06
    æ£Ĵ
    0.06
    åľ¨æĹł
    0.06
    èĴ²
    0.06
    ughty
    0.06
    æł¹æį®åĽ½å®¶
    0.06
    é»İæĺİ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.