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. 163657
    Prev
    Next
    INDEX
    Explanations

    planning and arrangements

    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
    åħįç¨İ
    -0.28
    orer
    -0.28
    [assembly
    -0.27
    ngo
    -0.27
    ningar
    -0.26
    nder
    -0.25
     bergen
    -0.24
    uais
    -0.24
    çĸ¤
    -0.24
    hazi
    -0.24
    POSITIVE LOGITS
    å®ļæĹ¶
    0.34
    æģ°å½ĵ
    0.30
    æĺİç¡®
    0.28
    éĢĤå½ĵ
    0.28
    个å°ı
    0.28
    æĮĩå®ļ
    0.28
    è§ĦåĪĴ
    0.28
    计åĪĴ
    0.28
     plans
    0.28
     rules
    0.27
    Activations Density 0.002%

    No Known Activations