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. 15194
    Prev
    Next
    INDEX
    Explanations

    Professional 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
    çĻ»
    -0.28
    çŃĭ
    -0.27
    FromArray
    -0.26
     LIB
    -0.25
     GA
    -0.25
    çĥŁèĬ±
    -0.24
    isans
    -0.24
    sez
    -0.24
     practically
    -0.24
    ioms
    -0.24
    POSITIVE LOGITS
    è¯Ħæµĭ
    0.25
    él
    0.25
     Knoxville
    0.24
    缨
    0.24
    LTR
    0.24
     \%
    0.24
    avelength
    0.24
     Bale
    0.23
    alleries
    0.23
    ropri
    0.23
    Activations Density 0.928%

    No Known Activations