© 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. 7796
    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
    æ´»
    -0.27
     transmissions
    -0.26
    intage
    -0.26
    åĢ¼å¾Ĺåħ³æ³¨
    -0.26
    ãģ¾ãģĦ
    -0.25
     exc
    -0.24
     transmission
    -0.24
    ãĤīãģĦ
    -0.24
     emerging
    -0.24
     assignments
    -0.24
    POSITIVE LOGITS
    Props
    0.28
     Props
    0.27
    bmp
    0.26
    zym
    0.25
    PROP
    0.25
    _PROP
    0.24
    _props
    0.24
    ç»Ŀ
    0.24
     props
    0.24
    ç»ĥ
    0.24
    Activations Density 0.363%

    No Known Activations

    This feature has no known activations.