© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    held liable

    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
    æĸ°åĬłåĿ¡
    -0.11
    ually
    -0.11
    ï¸İ
    -0.10
    ÌĢ
    -0.09
    ielle
    -0.09
    缸è¾ħ缸æĪIJ
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    ially
    -0.08
    ual
    -0.08
    à§įত
    -0.08
    POSITIVE LOGITS
    ä¸įä½ı
    0.11
    ings
    0.10
    erness
    0.10
    sworth
    0.09
    çĿĢçļĦ
    0.09
    ä¸įä½ıäºĨ
    0.09
     sway
    0.08
    çĿĢä¸Ģ
    0.08
    Ùģظ
    0.08
    å¾Ĺä½ı
    0.08
    Activations Density 0.040%

    No Known Activations