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. 162173
    Prev
    Next
    INDEX
    Explanations

    Ordinal numbers

    np_max-act · gemini-2.0-flash
    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
    缸
    -0.28
    å·¥
    -0.28
    AX
    -0.27
    ax
    -0.27
    å®¶ä¼Ļ
    -0.26
    logic
    -0.26
    Buffer
    -0.25
    buf
    -0.25
    buff
    -0.25
    bu
    -0.25
    POSITIVE LOGITS
    setParameter
    0.27
    åĴĿ
    0.24
    ','#
    0.24
    åѦä¸ļ
    0.24
    iosk
    0.23
     pund
    0.23
    èĮģ
    0.23
    _Equals
    0.23
    comes
    0.23
    =out
    0.23
    Activations Density 0.015%

    No Known Activations