© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8625
    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
    urious
    -0.26
    òa
    -0.25
     ?.
    -0.25
     sack
    -0.25
    Hint
    -0.25
     Hint
    -0.24
     clue
    -0.24
    åı¯åĪĨ为
    -0.24
    _hint
    -0.24
     ogl
    -0.24
    POSITIVE LOGITS
    ä»ĸå°±
    0.28
    ä¼ĺåĬ¿
    0.27
    à¤ł
    0.27
    åĪ°çİ°åľ¨
    0.26
    ç»´å°Ķ
    0.25
    -tab
    0.24
    tab
    0.24
    èĩ³ä»Ĭ
    0.24
    æīĵéĢłåĩº
    0.24
    çIJĨæĥ³
    0.24
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.