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. 15113
    Prev
    Next
    INDEX
    Explanations

    goal, objective, aim

    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
    amus
    -0.26
    -sync
    -0.26
    çł
    -0.26
    èĩªçIJĨ
    -0.25
    年第
    -0.24
     mouths
    -0.24
     Away
    -0.24
    衾
    -0.24
    å§ļæĺİ
    -0.23
    located
    -0.23
    POSITIVE LOGITS
     of
    0.48
     reducing
    0.34
    of
    0.33
    à¸Ĥà¸Ńà¸ĩ
    0.30
    building
    0.30
    _of
    0.30
     cá»§a
    0.30
     to
    0.29
     building
    0.28
     generating
    0.28
    Activations Density 0.008%

    No Known Activations