© 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. 6439
    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
    oram
    -0.28
    çį¨ç«ĭ
    -0.26
    oris
    -0.25
     bureaucracy
    -0.25
    èĢĮä¸į
    -0.25
     independ
    -0.25
    éĿ¢åħ·
    -0.24
    æĪij说
    -0.24
     [&
    -0.24
    -Up
    -0.23
    POSITIVE LOGITS
    æĹĹ
    0.28
    AGO
    0.28
    次
    0.25
    (nullable
    0.25
    +',
    0.24
    èĩªå¾ĭ
    0.24
    ள
    0.24
    .TO
    0.23
    ä¿®
    0.23
    è¯ĥ
    0.23
    Activations Density 0.062%

    No Known Activations

    This feature has no known activations.