© 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. 106891
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical concepts

    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
    venience
    -0.25
    (fragment
    -0.25
    ingham
    -0.24
    åįĹè·¯
    -0.24
    就说
    -0.24
    .Fragment
    -0.24
    ä¸įæĸ¹ä¾¿
    -0.23
    +l
    -0.23
    æĹĹèĪ°
    -0.23
    exion
    -0.23
    POSITIVE LOGITS
    );\
    0.27
    lor
    0.27
    -away
    0.26
     neighbourhood
    0.26
    ĸī
    0.25
     population
    0.24
     populace
    0.24
    -offs
    0.24
    lfw
    0.24
     aw
    0.24
    Activations Density 21.231%

    No Known Activations