© 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. 140735
    Prev
    Next
    INDEX
    Explanations

    Technical, scientific

    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
     rects
    -0.30
    Rect
    -0.28
    _rect
    -0.28
    å¸Ń
    -0.27
    lush
    -0.27
    缮åīįå·²
    -0.26
    pray
    -0.25
    è´¨
    -0.25
    æĿĢæŃ»
    -0.25
    èIJ¤
    -0.25
    POSITIVE LOGITS
    anging
    0.29
    com
    0.27
    hunt
    0.25
    compressed
    0.25
     utf
    0.25
    _est
    0.25
    ron
    0.24
    åħ¼å®¹
    0.24
     comic
    0.24
    cling
    0.24
    Activations Density 7.432%

    No Known Activations