© 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. 33158
    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
    atra
    -0.07
    ī¬
    -0.07
     harmon
    -0.07
    yh
    -0.07
    设æľī
    -0.07
    çħľ
    -0.06
    yti
    -0.06
    osi
    -0.06
    交æµģå¹³åı°
    -0.06
    ey
    -0.06
    POSITIVE LOGITS
    обе
    0.08
    ãĥªãĥ¼ãĥ³
    0.07
    两ç§įæĸ¹å¼ı
    0.07
    prud
    0.07
    ç¨ĭåºıçļĦ
    0.07
    çİĭ大
    0.07
    两å¤Ħ
    0.07
    á»Ļn
    0.07
    æµĵæµĵçļĦ
    0.07
    ä¸ĸçķĮçļĦ
    0.07
    Activations Density 0.000%

    No Known Activations