© 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. 38794
    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
    éd
    -0.29
     perman
    -0.27
     dipped
    -0.26
    idon
    -0.25
    vara
    -0.25
    åij¢
    -0.24
    æĽĿåħī
    -0.24
    unda
    -0.23
    ember
    -0.23
    cents
    -0.23
    POSITIVE LOGITS
    éĶĨ
    0.27
    çĻ½äºij
    0.26
     Apt
    0.25
    IOR
    0.25
    _prompt
    0.24
     indicated
    0.24
     Voy
    0.24
    пÑĥÑĤ
    0.24
    lek
    0.24
    ty
    0.23
    Activations Density 30.699%

    No Known Activations

    This feature has no known activations.