© 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. 9008
    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
    âĸ¶
    -0.07
    èijĹåIJįçļĦ
    -0.06
    (KP
    -0.06
    ðŁ
    -0.06
     simplified
    -0.06
    âĸ·
    -0.06
    ocusing
    -0.06
    æľ¬ä½ľ
    -0.06
     specializing
    -0.06
    âĹİ
    -0.06
    POSITIVE LOGITS
    æł¹æľ¬å°±æĺ¯
    0.09
    ä¸įåı¯æĢķ
    0.08
    rania
    0.08
    carlo
    0.08
    åıĪæĺ¯ä¸Ģ个
    0.08
    emberg
    0.08
    ä¿¡æģ¯ç½ij
    0.08
    âĢIJ
    0.08
    çļĦéĤ£ä¸ªäºº
    0.08
    çĦ¶å¤§
    0.08
    Activations Density 0.000%

    No Known Activations