© 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. 56674
    Prev
    Next
    INDEX
    Explanations

    verbs followed by common articles/conjunctions

    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
    缮çļĦæĺ¯ä¸ºäºĨ
    -0.11
    为äºĨä¿Ŀè¯ģ
    -0.11
    为äºĨ
    -0.10
    çĤºäºĨ
    -0.10
    æĺ¯ä¸ºäºĨ
    -0.10
    为äºĨä¿ĿæĬ¤
    -0.10
    为äºĨæıIJé«ĺ
    -0.10
    为åĬłå¼º
    -0.09
    为æݨåĬ¨
    -0.09
    æĺ¯çĤºäºĨ
    -0.09
    POSITIVE LOGITS
    æīįè¡Į
    0.08
     terlebih
    0.07
    VD
    0.07
    :
    0.07
    enstr
    0.07
    —but
    0.06
    KL
    0.06
    çī¹æĦı
    0.06
    å¨ħ
    0.06
    èĬ®
    0.06
    Activations Density 0.507%

    No Known Activations