© 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. 14305
    Prev
    Next
    INDEX
    Explanations

    fusion, import, bonding, recognition, TVs, panels, diseases, making

    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
    缸åºĶ
    -0.06
    åľ¨æŃ¤æľŁéĹ´
    -0.06
    (-
    -0.06
    ç»ı
    -0.06
    ิà¸Ķ
    -0.06
    çIJ¥
    -0.06
    çļĦä½ľçĶ¨ä¸ĭ
    -0.06
    çĮ¿
    -0.06
    åıĸèĢĮ代ä¹ĭ
    -0.06
    åħĥ
    -0.06
    POSITIVE LOGITS
    æľīå¾Īå¤ļç§į
    0.11
     typically
    0.10
     generally
    0.10
    å¾Ģå¾Ģ
    0.10
     often
    0.10
     usually
    0.09
    éĢļ常æĺ¯
    0.09
    å¾Ģå¾Ģæĺ¯
    0.09
    ä¸ĢèĪ¬éĩĩçĶ¨
    0.09
    éĢļ常éľĢè¦ģ
    0.09
    Activations Density 0.040%

    No Known Activations