© 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. 63491
    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
    ãĥ¢ãĥ³
    -0.25
    agra
    -0.24
    åħ¸
    -0.24
    UCE
    -0.24
     каÑĤал
    -0.24
    APS
    -0.24
    ãģ¤ãģĭ
    -0.23
    Trip
    -0.23
    .son
    -0.23
     ((((
    -0.23
    POSITIVE LOGITS
     lod
    0.26
    æĽ´å¤ļä¿¡æģ¯
    0.25
    讵
    0.24
    ints
    0.23
    ldb
    0.23
    lfw
    0.23
     vestib
    0.23
    æĦĪ
    0.23
    追究
    0.23
    Ùģاء
    0.23
    Activations Density 7.676%

    No Known Activations

    This feature has no known activations.