© 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. 55731
    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
    使å®ĥ
    -0.08
    æİĪæĿĥèĮĥåĽ´åĨħ使çĶ¨
    -0.07
    人说
    -0.07
    åħ¶å®ŀæĺ¯
    -0.07
     constant
    -0.07
    æĪĺçķ¥æĢ§
    -0.07
    åĥıä¸Ģ个
    -0.07
    åıĪåIJį
    -0.07
    æĬĬæīĢæľī
    -0.07
    ĤŃ
    -0.06
    POSITIVE LOGITS
    å±ĬæŶ
    0.09
    ä¾Ŀæį®
    0.08
    ä½łçļĦæľĭåıĭ
    0.08
    åºĶå½ĵåIJij
    0.08
    åħ·ä½ĵåĪĨæŀIJ
    0.08
    äºĮ审
    0.08
    è¾ĥ为
    0.08
    iba
    0.08
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    0.08
    并éĿŀæĺ¯
    0.08
    Activations Density 0.000%

    No Known Activations