© 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. 108180
    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
    ór
    -0.31
    åħ¬
    -0.27
    formula
    -0.24
    vez
    -0.23
    ivic
    -0.23
    èݲèĬ±
    -0.23
    ç
    -0.23
     change
    -0.23
     constexpr
    -0.22
     aktiv
    -0.22
    POSITIVE LOGITS
    åĬĽæ±Ĥ
    0.27
     Dix
    0.26
    radouro
    0.26
    gle
    0.26
    ogen
    0.25
     Material
    0.25
    FLOW
    0.24
     irrelevant
    0.24
    ume
    0.24
    ulumi
    0.24
    Activations Density 1.936%

    No Known Activations

    This feature has no known activations.