© 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. 141729
    Prev
    Next
    INDEX
    Explanations

    Common stop words/punctuation

    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
    TI
    -0.30
    /pub
    -0.27
    flix
    -0.27
    [vi
    -0.26
    :num
    -0.26
    stants
    -0.25
    кла
    -0.24
    sehen
    -0.24
    imes
    -0.24
    cko
    -0.24
    POSITIVE LOGITS
    abe
    0.26
     foul
    0.25
     Harding
    0.23
    ForMember
    0.23
    abad
    0.23
    ragment
    0.23
    l
    0.23
    饱åĴĮ
    0.23
     ste
    0.23
     surrounding
    0.23
    Activations Density 15.649%

    No Known Activations