© 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. 4709
    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
    èĢĮ对äºİ
    -0.28
    umblr
    -0.28
    mue
    -0.26
    à¸ŀà¸Ń
    -0.25
    ichier
    -0.25
    _singleton
    -0.25
    å¾Ĵ
    -0.24
    andez
    -0.24
     Revel
    -0.24
     numberOfRows
    -0.24
    POSITIVE LOGITS
    Inc
    0.28
    -follow
    0.27
     Inc
    0.27
    æįķæįī
    0.26
    bite
    0.26
    èĢĥéªĮ
    0.25
    -rec
    0.24
    _signed
    0.23
    -inc
    0.23
    .inc
    0.23
    Activations Density 0.219%

    No Known Activations

    This feature has no known activations.