© 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. 129473
    Prev
    Next
    INDEX
    Explanations

    Informal conversation or 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
    ocs
    -0.30
     darker
    -0.26
    wei
    -0.26
    è¿ĺ
    -0.25
    åı¦å¤ĸ
    -0.24
     Oc
    -0.24
    Aw
    -0.24
    åļ¼
    -0.24
    itim
    -0.24
    åīįèĢħ
    -0.23
    POSITIVE LOGITS
    agues
    0.27
    veled
    0.25
    goo
    0.25
     blessed
    0.25
    affen
    0.24
    å¼Ń
    0.24
     skys
    0.24
    ottes
    0.24
     work
    0.23
    bens
    0.23
    Activations Density 18.851%

    No Known Activations