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. 162171
    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
    osphere
    -0.31
    db
    -0.28
     thr
    -0.28
     fron
    -0.27
     pos
    -0.27
    phere
    -0.26
     len
    -0.26
    çŁŃ线
    -0.26
    ]:=
    -0.26
     links
    -0.25
    POSITIVE LOGITS
     Indones
    0.27
    sse
    0.27
    VIC
    0.25
     GetEnumerator
    0.25
     stil
    0.24
    è¿Ļ个游æĪı
    0.24
    æļ´
    0.24
    imeType
    0.24
    aget
    0.24
    .dist
    0.24
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.