© 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. 129784
    Prev
    Next
    INDEX
    Explanations

    places

    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
    สà¸Ķ
    -0.29
    iets
    -0.27
    æ¸į
    -0.27
    -piece
    -0.26
    unda
    -0.24
    çĶ·
    -0.24
     machinery
    -0.24
    æĸ°è¥¿
    -0.24
    sal
    -0.24
    itor
    -0.23
    POSITIVE LOGITS
     afore
    0.26
    æĪIJè¯Ń
    0.25
     Ortiz
    0.25
     siècle
    0.24
     '{@
    0.24
     Evo
    0.24
     оÑĩеÑĢед
    0.24
     Sweep
    0.24
    åIJ¬å¾Ĺ
    0.24
    æ¡Įä¸Ĭ
    0.24
    Activations Density 14.641%

    No Known Activations