Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15147
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīå¤ļ
    -0.25
    éĻIJ度
    -0.25
    ulum
    -0.24
    stance
    -0.24
    omination
    -0.23
    claimer
    -0.23
    cation
    -0.23
    æľī大éĩıçļĦ
    -0.23
    带é¢Ĩ
    -0.23
    jas
    -0.23
    POSITIVE LOGITS
     the
    0.71
     something
    0.61
     those
    0.60
     a
    0.58
     another
    0.56
     an
    0.49
     what
    0.48
     their
    0.45
     someone
    0.45
     some
    0.43
    Activations Density 1.085%

    No Known Activations