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. 11-TRANSCODER-HP
    4. 53855
    Prev
    Next
    INDEX
    Explanations

    Scraped website text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFI
    -0.27
    >Loading
    -0.26
    	Con
    -0.26
    incorrect
    -0.25
    ixer
    -0.25
    igli
    -0.25
    æľīå¤ļ大
    -0.24
    sitemap
    -0.24
    hlen
    -0.24
    ieren
    -0.24
    POSITIVE LOGITS
    strap
    0.26
    .Unity
    0.25
     essay
    0.25
    åĥ®
    0.25
     ||=
    0.25
     onto
    0.25
    檫
    0.25
    "][
    0.25
     face
    0.25
     Ox
    0.24
    Activations Density 0.024%

    No Known Activations