© 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. 6206
    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
    羣çļĦæĺ¯
    -0.27
    è´¸
    -0.27
     Kare
    -0.27
     tys
    -0.26
    ÑĭÑĤа
    -0.25
    /Gate
    -0.25
    åīįæıIJ
    -0.25
    ä¸ĩäºĭ
    -0.24
    åħįè´£
    -0.24
     dads
    -0.24
    POSITIVE LOGITS
     Nicholson
    0.27
    æ³Ľ
    0.26
    pon
    0.25
    /month
    0.24
    uhl
    0.24
    pec
    0.24
    èĭ¥æľī
    0.24
     having
    0.24
    顶
    0.23
    etric
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.