© 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. 140859
    Prev
    Next
    INDEX
    Explanations

    Lists with numbers/letters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ieves
    -0.27
    zes
    -0.26
    &action
    -0.26
    æĸĭ
    -0.24
    ä¸Ķ
    -0.24
    ActionResult
    -0.24
    ç¼ħ
    -0.24
    ral
    -0.24
    apon
    -0.23
    gger
    -0.23
    POSITIVE LOGITS
    future
    0.28
    urpose
    0.28
    ä¸ĭåİ»
    0.26
    TING
    0.26
    åħ¥åı£
    0.25
    对ä¸ŃåĽ½
    0.25
    unch
    0.24
    W
    0.24
    0
    0.24
    ä¸ŃåĽ½çļĦ
    0.24
    Activations Density 44.054%

    No Known Activations