© 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. 141992
    Prev
    Next
    INDEX
    Explanations

    Snow, mountains, or 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
    æĪĸå¤ļ
    -0.31
     thiá»ĩn
    -0.27
     mix
    -0.24
     Mix
    -0.24
    .syntax
    -0.23
     connect
    -0.23
     share
    -0.23
    uable
    -0.23
    ----------------------------------------------------------------------
    -0.23
    åħģ
    -0.23
    POSITIVE LOGITS
    èĢģæŧ
    0.28
    èĮ¸
    0.27
    illator
    0.27
    cae
    0.26
    汶
    0.26
    seconds
    0.25
    å¤ļä¹Ī
    0.24
    æŀģ度
    0.24
     &[
    0.24
    á»Ļt
    0.24
    Activations Density 14.720%

    No Known Activations