© 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. 11414
    Prev
    Next
    INDEX
    Explanations

    ordered or unordered comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æīĢæľīè¿ĻäºĽ
    -0.08
     Pesc
    -0.08
    åľĪçļĦ
    -0.08
    èĢĮè¿ĻäºĽ
    -0.08
    åįĬéĢĶ
    -0.08
    驻马
    -0.08
    æŃ¤æ¥¼
    -0.08
    Ïĥμα
    -0.07
    agher
    -0.07
    åıĬæĹ©
    -0.07
    POSITIVE LOGITS
    é¢ł
    0.08
    æķ´çIJĨ
    0.08
    é¡
    0.07
    çIJĨ顺
    0.07
     Sorted
    0.07
     sorted
    0.07
    è¿Ľ
    0.07
     unordered
    0.06
    æķ¦
    0.06
    ä¸į管
    0.06
    Activations Density 0.004%

    No Known Activations