© 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. 141790
    Prev
    Next
    INDEX
    Explanations

    Patent/legal documents

    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
    yst
    -0.28
    yt
    -0.26
    ysts
    -0.25
    ÑĤоп
    -0.24
    橹
    -0.23
    天çĦ¶
    -0.23
    çģ«åĬĽ
    -0.23
    çİ°çĬ¶
    -0.23
     hypoc
    -0.23
    iv
    -0.23
    POSITIVE LOGITS
    inx
    0.26
    ueur
    0.25
    AGED
    0.24
    -LAST
    0.24
    ettes
    0.24
    ä¸İåħ¶ä»ĸ
    0.24
    ä¿Ĥ
    0.23
    å¼¹
    0.23
    oris
    0.23
    éĢ¶
    0.23
    Activations Density 10.205%

    No Known Activations