© 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. 61570
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by 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
    kaar
    -0.09
    表çݰ为
    -0.08
    åĪ¤å¤ĦæľīæľŁå¾ĴåĪij
    -0.08
    åģļçļĦå°±æĺ¯
    -0.08
    ož
    -0.08
    éĩı为
    -0.07
     afterward
    -0.07
     afterwards
    -0.07
    èĦı
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    POSITIVE LOGITS
    æŃ£åıį
    0.08
     despite
    0.07
     is
    0.07
     biome
    0.07
    ìłľëĬĶ
    0.07
    以åĪ©
    0.06
    èĢĥå¯Ł
    0.06
     argues
    0.06
    æĺ¯è¦ģ
    0.06
    haj
    0.06
    Activations Density 0.001%

    No Known Activations