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. 15295
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iams
    -0.26
    >Password
    -0.25
    creasing
    -0.24
    elpers
    -0.24
    éĺħ
    -0.23
    ष
    -0.23
     rés
    -0.23
    enge
    -0.23
    å¸Ļ
    -0.22
    riting
    -0.22
    POSITIVE LOGITS
    _OWNER
    0.30
    ä»°
    0.28
    -hit
    0.26
    è¾ĸ
    0.26
    cling
    0.25
    æĢ§æĦŁ
    0.25
    æĭįçħ§
    0.25
     legion
    0.25
    ύ
    0.25
    slot
    0.24
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.