© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130927
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
    Negative Logits
     recount
    -0.30
     doubling
    -0.27
     dest
    -0.27
     talents
    -0.26
     proceed
    -0.25
     destination
    -0.25
    ently
    -0.25
    åĬŀäºĭ
    -0.24
    oundation
    -0.24
    rated
    -0.24
    POSITIVE LOGITS
    vec
    0.28
    tam
    0.27
    £¼
    0.27
    osci
    0.26
    -<?
    0.26
     génér
    0.26
    å²Ķ
    0.25
    èĢĮæĪIJ
    0.25
    kbd
    0.25
    å¤ļå¹´åīį
    0.24
    Activations Density 0.983%

    No Known Activations