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. 23-TRANSCODER-HP
    4. 162280
    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
    à¸Ħà¸ĩ
    -0.30
    =~
    -0.27
     useParams
    -0.27
    Grand
    -0.25
    $i
    -0.25
    ighb
    -0.25
    _invoke
    -0.24
     rumor
    -0.24
    )i
    -0.24
    .peer
    -0.24
    POSITIVE LOGITS
    åı¸
    0.28
    寸
    0.26
     Passage
    0.26
    ernote
    0.25
    imations
    0.24
     Inches
    0.24
    å¯Ħ
    0.24
    è¾ľ
    0.24
    身
    0.24
     Accord
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.