© 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. 141049
    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
    ÑĢак
    -0.28
    earn
    -0.26
    DÄ°
    -0.25
    çĶŁåij½åĬĽ
    -0.25
    äºļ太
    -0.24
     commun
    -0.23
    æĢ§åij½
    -0.23
    .consume
    -0.23
     Appeal
    -0.23
    _msgs
    -0.23
    POSITIVE LOGITS
     fortn
    0.26
    gratis
    0.25
    ago
    0.24
    åħ¬åħ±æĸĩåĮĸ
    0.24
    atorium
    0.24
    èĥ½åģļåĪ°
    0.24
    åī¯æľ¬
    0.24
    _free
    0.24
    emony
    0.24
    IRTUAL
    0.24
    Activations Density 7.351%

    No Known Activations

    This feature has no known activations.