© 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. 63762
    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
    ungan
    -0.31
    inking
    -0.28
    bro
    -0.26
    ç«£
    -0.26
    éĩįä¸Ń
    -0.26
    ationToken
    -0.25
    edBy
    -0.24
    bane
    -0.24
    Boundary
    -0.24
    å³»
    -0.24
    POSITIVE LOGITS
     Tune
    0.23
    comfort
    0.23
    æĺ¨
    0.23
    -sm
    0.23
    Comfort
    0.23
    onic
    0.23
    æħķ容
    0.23
     prior
    0.23
    åĿ¡
    0.23
    竽
    0.23
    Activations Density 19.855%

    No Known Activations

    This feature has no known activations.