© 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. 33-TRANSCODER-HP
    7. 54654
    Prev
    Next
    INDEX
    Explanations

    farming, gardening

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    crop
    -0.40
    .crop
    -0.36
    åĨľ
    -0.33
     crop
    -0.32
    _crop
    -0.32
    ä½ľçī©
    -0.32
    Crop
    -0.32
     cropping
    -0.31
    èݳ
    -0.30
    èķ¨
    -0.30
    POSITIVE LOGITS
    rer
    0.30
     t
    0.28
    éĻĨ
    0.27
    åŃ¦ä¹ł
    0.26
     tends
    0.26
    æīŃ转
    0.25
     ga
    0.25
     vô
    0.25
     container
    0.25
    aned
    0.24
    Activations Density 0.015%

    No Known Activations