© 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. 8232
    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
    Ñĥв
    -0.27
    人åı£
    -0.27
     question
    -0.27
    ild
    -0.26
     session
    -0.26
    ông
    -0.25
    å¾ĹçĽĬ
    -0.25
    question
    -0.25
     gre
    -0.24
    å²Ķ
    -0.24
    POSITIVE LOGITS
    pany
    0.29
     OPERATION
    0.27
    åĻ»
    0.26
     Operating
    0.26
    endforeach
    0.25
     wd
    0.25
    èŃ½
    0.25
     localize
    0.24
    awah
    0.23
     Pred
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.