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. 162106
    Prev
    Next
    INDEX
    Explanations

    code and copyright

    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
    borg
    -0.28
    èĤ©èĨĢ
    -0.26
    çĿ̥̿
    -0.25
    è¿İ
    -0.25
    æĬĽ
    -0.24
    mi
    -0.24
    çļĦåħ´è¶£
    -0.23
     Sahara
    -0.23
    âĹ»
    -0.23
    rons
    -0.23
    POSITIVE LOGITS
    Won
    0.30
    !!");↵
    0.27
    urity
    0.27
    .signals
    0.26
    won
    0.26
     pedig
    0.24
     nutrit
    0.24
    ulse
    0.24
    OCK
    0.24
    ugo
    0.24
    Activations Density 0.001%

    No Known Activations