© 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. 129853
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    nant
    -0.28
    дÑĢ
    -0.28
    :?
    -0.26
    :init
    -0.25
    :Object
    -0.25
     nominee
    -0.25
     terminals
    -0.24
    åįģä¸ĥæĿ¡
    -0.24
    大家ä¸Ģèµ·
    -0.24
     ram
    -0.24
    POSITIVE LOGITS
    ä¼łæĿ¥
    0.30
    osen
    0.28
    istani
    0.28
    ÑģÑĤвÑĥ
    0.27
    é¦ĸéĥ½
    0.25
    驹
    0.25
     ÐŁÐ°ÑĢ
    0.25
    ercicio
    0.24
     Kirk
    0.23
    IRON
    0.23
    Activations Density 1.253%

    No Known Activations

    This feature has no known activations.