© 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. 10812
    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
    над
    -0.08
    éĺ¿å§Ĩæĸ¯çī¹
    -0.08
    ervas
    -0.07
    omad
    -0.07
    æĶ¯æĴij
    -0.07
    cgi
    -0.07
    egah
    -0.06
    olla
    -0.06
    éļıçĿĢæŶéĹ´çļĦ
    -0.06
    float
    -0.06
    POSITIVE LOGITS
    /change
    0.10
    æĶ¹åıĺ
    0.10
    çļĦæĶ¹åıĺ
    0.09
    estra
    0.09
    è·ĥ
    0.08
     abrupt
    0.08
     change
    0.08
    change
    0.08
    æĶ¹åıĺäºĨ
    0.08
     changer
    0.08
    Activations Density 0.000%

    No Known Activations