© 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. 8395
    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
    fram
    -0.28
    bris
    -0.25
     ({↵
    -0.25
     Stall
    -0.25
    ÃŃda
    -0.24
    iterals
    -0.24
     {});↵↵
    -0.24
    ino
    -0.24
    éĽĨåĽ¢èĤ¡ä»½
    -0.24
     IonicPage
    -0.23
    POSITIVE LOGITS
     mug
    0.27
    çĻ¸
    0.27
     function
    0.27
    ãĥĺãĥ«
    0.24
     prompt
    0.24
    _METADATA
    0.24
    uchos
    0.23
    ibles
    0.23
     обÑĥÑĩениÑı
    0.23
    semble
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.