© 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. 6954
    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
    iare
    -0.25
    æģ¯æģ¯
    -0.24
    AccessException
    -0.24
    iasi
    -0.24
    èĢį
    -0.24
    æľīå¾ħ
    -0.23
     dial
    -0.23
    enty
    -0.23
    uckles
    -0.23
    alus
    -0.23
    POSITIVE LOGITS
    浪
    0.28
     ngân
    0.27
    éķľ
    0.27
    象å¾ģ
    0.26
    轨
    0.26
    éı¡
    0.26
    çıł
    0.26
    пÑĢом
    0.25
    mirror
    0.24
    èĭ
    0.24
    Activations Density 0.202%

    No Known Activations

    This feature has no known activations.