© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64042
    Prev
    Next
    INDEX
    Explanations

    as

    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
    lessly
    -0.29
    .telegram
    -0.27
    lift
    -0.27
    azes
    -0.27
     gol
    -0.25
    ä¸ĢåĽ¢
    -0.25
    éĿĻçĶµ
    -0.25
    举起
    -0.24
    èļ±
    -0.24
    æĢ»éĺŁ
    -0.24
    POSITIVE LOGITS
    å¾®
    0.28
    pcs
    0.24
     proced
    0.24
    czy
    0.24
    ine
    0.24
    Flo
    0.23
    ç°ĩ
    0.23
     rear
    0.23
    implicit
    0.23
    INE
    0.23
    Activations Density 19.964%

    No Known Activations