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. 163261
    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
     optic
    -0.26
    åĽŀå½Ĵ
    -0.26
     fireworks
    -0.25
     aspire
    -0.25
     Buccane
    -0.25
    _HOLD
    -0.24
    æ¡Ĩ
    -0.24
    woff
    -0.24
    &S
    -0.23
     forc
    -0.23
    POSITIVE LOGITS
    izar
    0.28
    ç¢į
    0.27
     rendre
    0.26
     ÑĢаÑģпÑĢоÑģÑĤÑĢанен
    0.26
    ante
    0.25
    åħĪè¡Į
    0.25
    *d
    0.24
    ari
    0.24
    ç»Ļèĩªå·±
    0.24
    çĭ¬ç«ĭ
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.