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. 15130
    Prev
    Next
    INDEX
    Explanations

    Programming code and text

    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
    arin
    -0.27
     credit
    -0.27
    eto
    -0.26
    éħį
    -0.26
    acen
    -0.25
     rushed
    -0.25
    paired
    -0.24
    éħįæľī
    -0.24
    mdir
    -0.24
    çķĪ
    -0.24
    POSITIVE LOGITS
    客
    0.36
    æŃĩ
    0.29
     Armour
    0.27
    iphers
    0.25
    stantiate
    0.25
    精确
    0.25
    åįķ车
    0.25
    egg
    0.24
     ATK
    0.24
    Exact
    0.24
    Activations Density 0.000%

    No Known Activations