© 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. 63760
    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
    ç»´å°Ķ
    -0.26
    errick
    -0.25
    æŃ¤ä¸¾
    -0.25
     UIT
    -0.24
     Catch
    -0.24
    åħ¬çĦ¶
    -0.24
    eldon
    -0.24
    aily
    -0.23
    enade
    -0.23
    å¼ķåħ¥
    -0.23
    POSITIVE LOGITS
    cts
    0.27
    nts
    0.27
    åı¯æĢķçļĦ
    0.24
    abo
    0.24
     ÐłÐ¾Ñģ
    0.24
    lays
    0.24
    rops
    0.24
    layui
    0.23
    .TryParse
    0.23
    cff
    0.23
    Activations Density 2.808%

    No Known Activations

    This feature has no known activations.