© 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. 64459
    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
     mid
    -0.35
     noon
    -0.29
    .mid
    -0.26
     sterile
    -0.26
    (mid
    -0.24
     settlement
    -0.23
    mid
    -0.23
    é¢łè¦Ĩ
    -0.23
     house
    -0.23
    umbo
    -0.23
    POSITIVE LOGITS
    OAD
    0.32
    orial
    0.28
    åĩºè·¯
    0.28
    伺
    0.27
    å²Ķ
    0.26
    nearest
    0.26
    жд
    0.25
    ä¸ĢåĪĻ
    0.25
    ç§ĺ
    0.24
    .om
    0.24
    Activations Density 13.158%

    No Known Activations

    This feature has no known activations.