© 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. 142707
    Prev
    Next
    INDEX
    Explanations

    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
     outdoors
    -0.29
    positor
    -0.27
     narrow
    -0.27
    ate
    -0.26
    imo
    -0.26
    oft
    -0.25
     usually
    -0.24
    IMO
    -0.24
     normally
    -0.24
    å¾Ģå¾Ģæĺ¯
    -0.24
    POSITIVE LOGITS
    INDER
    0.29
    clist
    0.28
     CCP
    0.27
    onian
    0.27
    itches
    0.26
    ntax
    0.25
    ernote
    0.25
    ingly
    0.24
    otoxic
    0.24
    大家åĪĨ享
    0.24
    Activations Density 1.110%

    No Known Activations