© 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. 19-TRANSCODER-HP
    7. 8088
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Europe
    -0.26
     doubly
    -0.25
     å·
    -0.25
    bst
    -0.24
     Europe
    -0.24
    eref
    -0.24
    +E
    -0.24
     season
    -0.24
     babel
    -0.24
     E
    -0.24
    POSITIVE LOGITS
    çļĦ人çī©
    0.28
    æ¡¥æ¢ģ
    0.26
     LAP
    0.25
    ëĿ½
    0.25
    å±ķä½į
    0.25
    UDO
    0.25
    odu
    0.24
    idel
    0.24
    人çī©
    0.24
    ToPoint
    0.24
    Activations Density 0.037%

    No Known Activations

    This feature has no known activations.