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. 15232
    Prev
    Next
    INDEX
    Explanations

    2

    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
     lock
    -0.30
     Lock
    -0.30
     locks
    -0.29
    locking
    -0.28
    éĶģ
    -0.27
    (lock
    -0.27
    Locker
    -0.27
     sweeps
    -0.27
     draw
    -0.26
    çĶ»
    -0.26
    POSITIVE LOGITS
    çªĹå¤ĸ
    0.27
    çªģçł´
    0.26
    edition
    0.25
    orges
    0.25
    åij¼åIJ¸
    0.25
    空
    0.24
     Print
    0.24
    har
    0.24
     dish
    0.24
    Ãį
    0.23
    Activations Density 0.906%

    No Known Activations