© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7587
    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
    #/
    -0.28
    ']}'
    -0.26
    >Password
    -0.25
    acle
    -0.25
    swer
    -0.24
     táºŃn
    -0.24
    iego
    -0.24
    AIL
    -0.23
    ":"'
    -0.23
    gewater
    -0.23
    POSITIVE LOGITS
    羣å¿ĥ
    0.28
     Jets
    0.26
    !--
    0.25
    æľĪ亮
    0.25
    Nested
    0.24
     dipped
    0.24
    æ¿ĢåĬ¨
    0.24
     empt
    0.24
     renov
    0.24
     kob
    0.24
    Activations Density 0.084%

    No Known Activations

    This feature has no known activations.