© 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. 7403
    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
     quant
    -0.28
    ç®Ĺ
    -0.26
    гла
    -0.25
    isse
    -0.25
     Fox
    -0.24
    ntax
    -0.24
     stata
    -0.24
     alphabet
    -0.24
    åıijå±ķåİĨç¨ĭ
    -0.24
    çŃĶé¢ĺ
    -0.24
    POSITIVE LOGITS
     Speedway
    0.29
    åĨ¶
    0.26
    inker
    0.25
    etry
    0.24
    éĢį
    0.24
     getSource
    0.24
    cream
    0.24
    ãģĹãģĭãģªãģĦ
    0.23
    ä½łä¼ļ
    0.23
    çłľ
    0.23
    Activations Density 0.089%

    No Known Activations

    This feature has no known activations.