© 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. 130383
    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
     Lennon
    -0.26
    (Html
    -0.25
    scoped
    -0.24
    vi
    -0.24
     Mum
    -0.24
    åĩĿ
    -0.24
     Clothes
    -0.24
    .hy
    -0.24
     chap
    -0.23
    iet
    -0.23
    POSITIVE LOGITS
    ukan
    0.31
    带走
    0.29
    åĤ¬
    0.28
    è°ĥèĬĤ
    0.26
     forgiving
    0.25
    airy
    0.25
    cação
    0.25
    assy
    0.24
    ature
    0.24
    brate
    0.24
    Activations Density 6.889%

    No Known Activations

    This feature has no known activations.