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. 30-TRANSCODER-HP
    4. 15290
    Prev
    Next
    INDEX
    Explanations

    Sharing personal information/trials

    np_max-act-logits · 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
    æħİ
    -0.28
    /browse
    -0.27
    翼
    -0.27
     aprend
    -0.27
    缯
    -0.26
    Learn
    -0.26
    æĮĩåįĹ
    -0.26
    éĢģå¾Ģ
    -0.25
    å°ıå¿ĥ
    -0.25
     learns
    -0.25
    POSITIVE LOGITS
     try
    0.35
     dedicated
    0.33
     trial
    0.30
     mentally
    0.30
     challenge
    0.29
     TRY
    0.29
     physically
    0.29
     aisle
    0.29
     mass
    0.28
    Try
    0.28
    Activations Density 0.888%

    No Known Activations