© 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. 35-TRANSCODER-HP
    7. 38690
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ellig
    -0.29
    Americ
    -0.24
    entanyl
    -0.23
    çıħ
    -0.23
     emerged
    -0.23
     emerge
    -0.22
     visualize
    -0.22
     tall
    -0.22
    aging
    -0.22
    attern
    -0.22
    POSITIVE LOGITS
    -motion
    0.27
    "--
    0.27
    -moving
    0.26
    âݯ
    0.25
    -scroll
    0.25
    –
    0.25
    –and
    0.24
    6
    0.24
    -fit
    0.24
    5
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.