© 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. 130748
    Prev
    Next
    INDEX
    Explanations

    Numerical sequences

    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
    ATUS
    -0.25
     alphabet
    -0.25
    _skin
    -0.24
    Untitled
    -0.24
    ropa
    -0.24
    alphabet
    -0.23
     argc
    -0.23
    åįģéĩĮ
    -0.23
    methodVisitor
    -0.23
    ourses
    -0.23
    POSITIVE LOGITS
    æĺ¯ä»ĸ
    0.32
     plag
    0.28
    eel
    0.27
    åIJĥçļĦ
    0.27
     post
    0.27
    èIJ½
    0.27
     keyst
    0.26
     polled
    0.26
    åIJĥäºĨ
    0.25
    èIJ½ä¸ĭ
    0.24
    Activations Density 16.378%

    No Known Activations