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. 27-TRANSCODER-HP
    4. 941
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulp
    -0.28
    lint
    -0.27
    ly
    -0.27
     qualify
    -0.26
    ught
    -0.25
    addy
    -0.25
    IGH
    -0.25
    rys
    -0.25
     publisher
    -0.24
    qualities
    -0.24
    POSITIVE LOGITS
    icated
    0.31
    atron
    0.25
    .cloudflare
    0.25
    弩
    0.25
    æĽ²çº¿
    0.24
    itivity
    0.24
    etest
    0.24
    itic
    0.24
    zione
    0.23
     Woodward
    0.23
    Activations Density 0.001%

    No Known Activations