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. 162149
    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
     rehe
    -0.26
    etchup
    -0.25
     versions
    -0.25
    è¿Ļ两天
    -0.24
    æĬ¥è®°èĢħ
    -0.24
     needs
    -0.24
     reim
    -0.24
    æ¡ģ
    -0.24
    让人们
    -0.24
    ROWS
    -0.23
    POSITIVE LOGITS
    à¤Ī
    0.27
    kers
    0.26
    ILD
    0.25
    ừa
    0.25
    ker
    0.24
    agascar
    0.24
    berra
    0.24
    çĵ¶é¢Ī
    0.24
    su
    0.24
    ammer
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.