© 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. 60865
    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
    teras
    -0.09
    пÑĮ
    -0.08
    figcaption
    -0.08
    äºĨ解èĩªå·±
    -0.08
    äºĨ解èĩªå·±çļĦ
    -0.08
     Bagno
    -0.08
     пÑĢоÑģÑĤÑĥ
    -0.08
    äºĨ解ä¼ģä¸ļ
    -0.08
    为å®ĺ
    -0.07
    为好åıĭ
    -0.07
    POSITIVE LOGITS
    0.07
    åıĬåħ¶åºĶçĶ¨
    0.07
    é¢ĩ
    0.06
    æ¶Ī
    0.06
    Âł
    0.06
    i
    0.06
    ÙĪر
    0.06
    iril
    0.06
    rimon
    0.06
    0.06
    Activations Density 0.000%

    No Known Activations