© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4941
    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
    illi
    -0.32
    ISTRY
    -0.28
     gu
    -0.27
     quadr
    -0.27
    ual
    -0.27
    å¿«éĢŁ
    -0.26
     Cookbook
    -0.26
     numbering
    -0.25
    alu
    -0.25
    arella
    -0.24
    POSITIVE LOGITS
    mps
    0.28
    .remaining
    0.26
    tero
    0.25
    çĵ®
    0.25
    roscope
    0.24
     indefinitely
    0.24
     accuse
    0.24
    ,vector
    0.23
     democrat
    0.23
    çľł
    0.23
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.