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. 15280
    Prev
    Next
    INDEX
    Explanations

    overly sensitive reactions

    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
    duk
    -0.28
    mod
    -0.27
    è¿ĩ
    -0.27
    çľĭä¸įæĩĤ
    -0.26
    medium
    -0.26
    zek
    -0.25
    çľĭä¸įåĩº
    -0.25
    iel
    -0.25
    èķ¾
    -0.25
    .medium
    -0.25
    POSITIVE LOGITS
     concern
    0.29
    èѦ
    0.28
    -alpha
    0.28
    Concern
    0.28
    åī¡
    0.28
     keyed
    0.27
    çĶµä¿¡
    0.27
     setActive
    0.27
    åĪĽæĦı
    0.27
    -alert
    0.27
    Activations Density 0.004%

    No Known Activations