© 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. 7662
    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
    ä¼IJ
    -0.26
    íĮIJ
    -0.25
    iped
    -0.24
     Hag
    -0.24
    _HOR
    -0.24
    å¾®éĩı
    -0.23
    MASK
    -0.23
    utral
    -0.23
    æ¢Ĺ
    -0.23
    å¼ĤæĢ§
    -0.23
    POSITIVE LOGITS
    åºĬä½į
    0.25
     volta
    0.24
     dis
    0.24
    å§ĵåIJį
    0.23
    è¯ļæĦı
    0.23
     avenue
    0.23
     multin
    0.23
    phil
    0.23
    ened
    0.23
     Arsenal
    0.23
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.