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. 47199
    Prev
    Next
    INDEX
    Explanations

    HS

    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
     EMS
    -0.30
     Walls
    -0.27
    RAM
    -0.27
    Door
    -0.25
     confirm
    -0.25
    åĬłä»¥
    -0.25
    ocaust
    -0.25
     Rogers
    -0.25
     quantify
    -0.25
    _ram
    -0.24
    POSITIVE LOGITS
    oling
    0.28
    à¸Ńà¸Ķ
    0.26
     assigned
    0.26
    unction
    0.25
     pylint
    0.24
    .linkedin
    0.24
     Kısa
    0.24
    olini
    0.24
    reed
    0.24
    <Long
    0.24
    Activations Density 0.179%

    No Known Activations