© 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. 31363
    Prev
    Next
    INDEX
    Explanations

    titles and organizations

    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
    çĶ±å¸Ĥ
    -0.09
    çļĦä¸ĢåĪĩéĥ½
    -0.08
    çĶ±ä¸ŃåĽ½
    -0.08
    人被
    -0.08
    çĶ±ä¼ģä¸ļ
    -0.08
    )').
    -0.08
    çĶ±æĶ¿åºľ
    -0.08
    çĶ±
    -0.08
    çĶ±åħ¬åı¸
    -0.07
    åĪĻçĶ±
    -0.07
    POSITIVE LOGITS
    -appointed
    0.08
    åľ¨å®ĮæĪIJ
    0.07
     setempat
    0.07
    并ç»ı
    0.07
    æł¹æį®åħ¶
    0.07
    å®¡æł¸åIJİ
    0.07
    æĪĸåħ¶
    0.07
    å¾Ĺ天
    0.07
    æĮĩçĿĢ
    0.07
     bersangkutan
    0.06
    Activations Density 0.988%

    No Known Activations