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. 163265
    Prev
    Next
    INDEX
    Explanations

    URLs, code, legal citations

    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
    Mailer
    -0.28
     Layers
    -0.27
    sym
    -0.26
     signatures
    -0.26
    aidu
    -0.26
    ledge
    -0.25
    ests
    -0.25
     destabil
    -0.25
     Lara
    -0.24
     testcase
    -0.24
    POSITIVE LOGITS
    ษา
    0.27
    ymous
    0.27
    åħ¶å®ŀ
    0.26
     ultimate
    0.26
    ulously
    0.25
    ä¼ģä¸ļ管çIJĨ
    0.25
    kin
    0.24
    arrow
    0.24
    æĹ¶ä¸į
    0.24
    ç»ĵ
    0.24
    Activations Density 0.007%

    No Known Activations