© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141371
    Prev
    Next
    INDEX
    Explanations

    Code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tera
    -0.28
     order
    -0.25
    kol
    -0.25
    plat
    -0.24
     Bars
    -0.24
    bery
    -0.24
     prep
    -0.24
    <pre
    -0.23
    loo
    -0.23
    åľ°åįĢ
    -0.23
    POSITIVE LOGITS
    ensive
    0.28
    éķ¿å¾Ĺ
    0.27
    uchi
    0.26
    ervers
    0.26
    穷人
    0.26
    çıłå®Ŀ
    0.25
    SSI
    0.25
    åĨħ马
    0.24
    chema
    0.24
     soph
    0.24
    Activations Density 4.408%

    No Known Activations