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. 15083
    Prev
    Next
    INDEX
    Explanations

    code and copyright information

    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
     Honour
    -0.27
     пÑĢог
    -0.26
    -forward
    -0.26
    严éĩįçļĦ
    -0.25
     blobs
    -0.25
     inputFile
    -0.25
     robert
    -0.25
     Forward
    -0.25
    æīĵäºĨ
    -0.25
    ç¦Ģ
    -0.25
    POSITIVE LOGITS
     ÑįкономиÑĩеÑģк
    0.27
    oola
    0.27
    reat
    0.26
     submar
    0.24
    è¯ŀ
    0.24
    astes
    0.23
    ooth
    0.23
    æħķ
    0.23
     crypt
    0.23
    oram
    0.23
    Activations Density 0.100%

    No Known Activations