© 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. 107068
    Prev
    Next
    INDEX
    Explanations

    atty

    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
     Che
    -0.26
    æļ¨
    -0.26
    implicit
    -0.26
    éĽĨ群
    -0.25
    -Ch
    -0.24
    çIJĨ工大åѦ
    -0.24
    adget
    -0.24
    履约
    -0.24
    ${
    -0.24
     Volume
    -0.24
    POSITIVE LOGITS
    åľ°
    0.28
    ä¸įçĶĺ
    0.27
    born
    0.26
    evity
    0.26
    太è¿ĩ
    0.25
     tongues
    0.25
    è¾ķ
    0.25
    gles
    0.25
    ately
    0.24
    åľ°çľĭçĿĢ
    0.24
    Activations Density 25.116%

    No Known Activations