© 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. 6497
    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
    weis
    -0.26
    TOR
    -0.26
    åı¶
    -0.26
    ishly
    -0.24
     toch
    -0.24
    sheet
    -0.24
    -sp
    -0.23
    áŀĤ
    -0.23
    liner
    -0.23
    _descr
    -0.23
    POSITIVE LOGITS
    ä¸¤å¼ł
    0.25
    fällig
    0.24
    æľī大éĩıçļĦ
    0.24
    (crate
    0.24
    å°º
    0.24
    çŃīæĸ¹éĿ¢çļĦ
    0.23
    ä¸ĢåĪĻ
    0.23
    agit
    0.23
    ä¸Ģæīĭ
    0.23
    侧
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.