© 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. 29587
    Prev
    Next
    INDEX
    Explanations

    verb forms followed by verbs/adjectives

    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
    éĶĻçļĦ
    -0.09
     chừng
    -0.08
    åıªåı¯æĥľ
    -0.08
    伦å¤ļ
    -0.08
    embed
    -0.07
    æĽ´åı¯
    -0.07
    çİĭ女士
    -0.07
    æĽ´å°ij
    -0.07
    å¤ªè¿ľ
    -0.07
    åıij表æĪĸ
    -0.07
    POSITIVE LOGITS
    oused
    0.07
     tasked
    0.07
    ijan
    0.07
    èĥ¤
    0.07
     Applied
    0.07
    iniai
    0.07
    heb
    0.07
     applied
    0.06
    ((__
    0.06
    mada
    0.06
    Activations Density 0.119%

    No Known Activations