© 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. 142649
    Prev
    Next
    INDEX
    Explanations

    ic

    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
    nl
    -0.27
    MLE
    -0.27
     '",
    -0.26
    ãĥ«ãĥī
    -0.25
    ấp
    -0.25
     Foundation
    -0.24
     dispatched
    -0.24
     congratulate
    -0.24
    testdata
    -0.24
    åĨįéĢł
    -0.24
    POSITIVE LOGITS
     Args
    0.29
    Args
    0.29
    ingroup
    0.27
     Lastly
    0.26
    aign
    0.26
    zin
    0.26
    argas
    0.26
    æĪŁ
    0.26
     disproportionately
    0.25
     invers
    0.25
    Activations Density 12.239%

    No Known Activations