© 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. 64788
    Prev
    Next
    INDEX
    Explanations

    project

    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
    thing
    -0.30
     disp
    -0.26
    åİļåİļ
    -0.25
    _Word
    -0.24
     Disp
    -0.24
     Ef
    -0.24
     Spread
    -0.24
    ellow
    -0.24
    resh
    -0.23
    ÙĤÙĨ
    -0.23
    POSITIVE LOGITS
     assignments
    0.26
    ully
    0.25
    -collapse
    0.25
    LIKELY
    0.25
     qs
    0.24
     Tro
    0.24
    /system
    0.24
     financing
    0.24
    manual
    0.23
     careers
    0.23
    Activations Density 17.700%

    No Known Activations