© 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. 6879
    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
    @include
    -0.30
     Gather
    -0.25
    itecture
    -0.24
    èŀŃ
    -0.24
    paration
    -0.24
    åī©ä¸ĭ
    -0.24
    eterminate
    -0.23
    人人
    -0.23
    éĽī
    -0.23
    [assembly
    -0.23
    POSITIVE LOGITS
    é£İæ³¢
    0.25
     aVar
    0.25
    meer
    0.25
     prod
    0.24
     vars
    0.24
     alt
    0.24
    èģĶ社
    0.24
    esis
    0.24
    alte
    0.24
    поÑĢ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.