© 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. 107119
    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
    ican
    -0.29
    icked
    -0.26
    iden
    -0.26
    åħ¥ãĤĬ
    -0.26
    ice
    -0.25
    cit
    -0.25
    åħīæ»ij
    -0.25
    icide
    -0.25
    colm
    -0.25
    èħij
    -0.25
    POSITIVE LOGITS
    yards
    0.30
    æĹ¶ä»£çļĦ
    0.26
     districts
    0.25
    ä¸Ĭå¹´
    0.25
    æĹ¶ä»£
    0.25
    tour
    0.24
    MLS
    0.24
    ivant
    0.24
    oire
    0.24
    ä¼Ļ
    0.23
    Activations Density 5.926%

    No Known Activations

    This feature has no known activations.