© 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. 1203
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    对åºĶ
    -0.06
     Rij
    -0.06
    èĩ³å°ij
    -0.06
    å½Ĵ
    -0.06
     easily
    -0.06
    agner
    -0.06
    orda
    -0.06
    loh
    -0.06
    éĢĤåIJĪ
    -0.06
    ä¸įæĥĬ
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩ
    0.09
    adden
    0.09
     hendak
    0.08
     íķ¨
    0.08
    ến
    0.08
     _______,
    0.08
    æľī人说
    0.08
    ä¸Ģåī¯
    0.08
    æĪij說
    0.07
    ä¸Ģ个æĸ°çļĦ
    0.07
    Activations Density 0.228%

    No Known Activations