© 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. 12465
    Prev
    Next
    INDEX
    Explanations

    forwarded email dates

    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
    æĿ¥è¶Ĭ
    -0.08
    åħļæĢ»æĶ¯ä¹¦è®°
    -0.07
    管æīĢ
    -0.07
    第äºĮåIJį
    -0.07
    åıĪåı¯ä»¥
    -0.07
    kaar
    -0.07
    大åIJĥ
    -0.06
    åºĶçĶ±
    -0.06
    amah
    -0.06
    æ¸IJæ¸IJåľ°
    -0.06
    POSITIVE LOGITS
    åħ¬åı¸åĨħéĥ¨
    0.07
    åħ¨å¿ĥåħ¨æĦı
    0.07
     revan
    0.07
    åIJĦç§įåIJĦæł·
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    rink
    0.07
    è®¤è®¤çľŁçľŁ
    0.06
    agai
    0.06
     اØŃت
    0.06
    .nextLine
    0.06
    Activations Density 0.002%

    No Known Activations