© 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. 140640
    Prev
    Next
    INDEX
    Explanations

    new

    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
    zzle
    -0.27
    ç·ļä¸Ĭ
    -0.27
     simultaneously
    -0.26
     nh
    -0.26
    mouseover
    -0.26
    çģ«çĥ§
    -0.25
    å¤ľ
    -0.25
    idy
    -0.25
     ambit
    -0.25
    mo
    -0.25
    POSITIVE LOGITS
    åĬłæ·±
    0.28
     shr
    0.26
     offsetof
    0.26
    æĶ¶åĽŀ
    0.26
     номеÑĢ
    0.25
    ä»Ģ
    0.25
    西路
    0.25
    çĽ¾
    0.25
    number
    0.25
    raise
    0.24
    Activations Density 5.467%

    No Known Activations