© 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. 18240
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.09
    æĤ¨çļĦä½įç½®
    -0.08
    æľī天
    -0.08
    Ãłm
    -0.08
    umpf
    -0.07
    æĸ¯åį¡
    -0.07
     Dw
    -0.07
    éķ
    -0.07
    _printf
    -0.07
    áte
    -0.07
    POSITIVE LOGITS
    åıĬåħ¶
    0.07
    为主é¢ĺ
    0.06
     >::
    0.06
    åıijå±ķçļĦ
    0.06
     –
    0.06
    为主é¢ĺçļĦ
    0.06
    èĭ¥æľīæīĢæĢĿ
    0.06
    éĹ®é¢ĺçļĦ
    0.06
    æĹ¥çĽĬ
    0.06
    Ñģни
    0.06
    Activations Density 0.005%

    No Known Activations