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. 15098
    Prev
    Next
    INDEX
    Explanations

    computer-related content

    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
    r
    -0.32
    @a
    -0.30
    c
    -0.30
    j
    -0.29
    @c
    -0.28
     c
    -0.28
    &p
    -0.27
    @d
    -0.27
     p
    -0.27
     h
    -0.27
    POSITIVE LOGITS
    éŀł
    0.26
     RELEASE
    0.24
    ç¨įç¨į
    0.24
    çķĻè¨ĢæĿ¿
    0.24
     Sha
    0.24
     cáo
    0.24
    YPE
    0.23
    licable
    0.23
    åŃĺ
    0.23
    spender
    0.23
    Activations Density 0.975%

    No Known Activations