© 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. 49824
    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
    å¼Ģå§ĭåľ¨
    -0.07
     daarvan
    -0.07
    ä¸İåħ¶
    -0.07
    ä¸Ģæ¡£
    -0.07
     commodo
    -0.07
    rieb
    -0.07
    赤水
    -0.07
    ieste
    -0.07
    eva
    -0.07
     diye
    -0.07
    POSITIVE LOGITS
    å§Ķ
    0.07
    öö
    0.07
    èªĵè¯į
    0.07
     Schwartz
    0.07
    ject
    0.07
    intersect
    0.07
    긴
    0.06
    å®
    0.06
    -svg
    0.06
    éĿ¢éĿ¢
    0.06
    Activations Density 0.000%

    No Known Activations