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. 162167
    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
    çĺ´
    -0.26
     TEX
    -0.26
     tilt
    -0.26
    xis
    -0.25
    æĻļ
    -0.25
    Ĭ¶
    -0.24
    ventions
    -0.24
    oogle
    -0.24
    躺çĿĢ
    -0.24
     affiliation
    -0.23
    POSITIVE LOGITS
    ein
    0.25
    [/
    0.25
     hub
    0.25
    _[
    0.24
    Operators
    0.24
    eye
    0.24
    nown
    0.24
     (~(
    0.24
    emark
    0.24
     operator
    0.23
    Activations Density 0.076%

    No Known Activations

    This feature has no known activations.