© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and states

    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
     pouvoir
    -0.10
    åı¯èĥ½çļĦ
    -0.10
     kunna
    -0.09
    åı¯èĥ½è¦ģ
    -0.09
     ability
    -0.09
     Ability
    -0.09
    åı¯ä¸įæĺ¯
    -0.09
     possibili
    -0.09
    åı¯èĥ½è¢«
    -0.09
    èĥ½å¤Łåľ¨
    -0.09
    POSITIVE LOGITS
     fácilmente
    0.14
     easily
    0.13
    ä¹Łåı¯ä»¥æĺ¯
    0.13
    ä¹Łåı¯ä»¥åľ¨
    0.12
    ä¹Łåı¯ä»¥ä½¿çĶ¨
    0.12
     anytime
    0.12
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.12
     بسÙĩÙĪÙĦØ©
    0.12
    ä¹Łåı¯ä»¥çĶ¨
    0.11
     Ñĥгодно
    0.11
    Activations Density 0.765%

    No Known Activations