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. 15198
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    ivals
    -0.31
    ground
    -0.31
    -ground
    -0.28
     ground
    -0.28
     valued
    -0.27
    aine
    -0.26
    ennen
    -0.26
    _shell
    -0.26
     trusts
    -0.26
    -unit
    -0.26
    POSITIVE LOGITS
     accom
    0.30
    IDL
    0.27
    iever
    0.26
    pz
    0.25
    æĪ¿è´·
    0.25
     Investig
    0.25
    è¿ĶåĽŀæIJľçĭIJ
    0.25
    æIJı
    0.24
    ptype
    0.24
    æĭİ
    0.24
    Activations Density 0.883%

    No Known Activations