© 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. 63661
    Prev
    Next
    INDEX
    Explanations

    incomplete "to" phrases/code

    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
     Metro
    -0.26
    èĥĮ
    -0.25
    /terms
    -0.25
    rances
    -0.24
    rieved
    -0.24
    Metro
    -0.24
     NOI
    -0.23
    sters
    -0.23
    /ss
    -0.23
     Barrett
    -0.23
    POSITIVE LOGITS
    ç»Ŀ大éĥ¨åĪĨ
    0.29
    å°±è·Ł
    0.26
    .wr
    0.25
     already
    0.25
     mere
    0.24
    ìĻķ
    0.24
    å°±æĬĬ
    0.24
     right
    0.24
     Similar
    0.23
    大å¹ħ度
    0.23
    Activations Density 35.964%

    No Known Activations