© 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. 11387
    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
    æīĴ
    -0.08
    çĦ¶å¤§
    -0.07
    icer
    -0.07
    rop
    -0.07
    scp
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    åĬ¨æīĭ
    -0.06
    .once
    -0.06
    åĬ«
    -0.06
    件
    -0.06
    POSITIVE LOGITS
    anship
    0.07
    aily
    0.07
    ìŬ
    0.07
    æľīæīĢäºĨ解
    0.07
    ừng
    0.06
     Haup
    0.06
    ạp
    0.06
     prém
    0.06
    ãģ¶
    0.06
    ìķ
    0.06
    Activations Density 0.000%

    No Known Activations