© 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. 130130
    Prev
    Next
    INDEX
    Explanations

    web text fragments

    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
    åŃĹæł·
    -0.43
    åŃĹ
    -0.40
     word
    -0.33
     spelled
    -0.31
     åŃĹ
    -0.30
    æĮĩ
    -0.30
    åIJį称
    -0.29
    å§ĵ
    -0.29
     plural
    -0.29
     cad
    -0.29
    POSITIVE LOGITS
    ialis
    0.35
    imet
    0.27
    ivic
    0.27
    æŀķ
    0.26
    ulton
    0.26
    inke
    0.26
    Êĭ
    0.26
    ä¸ĢæĹı
    0.25
    imat
    0.25
    upe
    0.25
    Activations Density 31.334%

    No Known Activations