© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7408
    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
    edom
    -0.27
    å®ŀåľ¨
    -0.26
     union
    -0.26
    .GetName
    -0.25
    union
    -0.25
     @}
    -0.25
    .Dom
    -0.24
    utton
    -0.24
    elib
    -0.24
    åľĪ
    -0.24
    POSITIVE LOGITS
    gallery
    0.25
    éĩijæ²Ļ
    0.25
    sten
    0.24
    Ùģائ
    0.24
    HEST
    0.24
    ÃŁe
    0.24
    CM
    0.23
    ê¸Īìľµ
    0.23
    inals
    0.23
    acam
    0.23
    Activations Density 0.243%

    No Known Activations

    This feature has no known activations.