© 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. 8186
    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
    人æĢ§
    -0.27
    ahu
    -0.27
    gang
    -0.27
    _invoke
    -0.26
    èĩº
    -0.25
    Bond
    -0.25
    åı°éĺ¶
    -0.25
     Borg
    -0.25
    åĭ
    -0.25
    ç«ŁçĦ¶
    -0.25
    POSITIVE LOGITS
    sus
    0.27
     suspension
    0.27
     sus
    0.25
     brid
    0.25
    ptive
    0.24
     bir
    0.24
    æīĢåľ¨
    0.24
     late
    0.23
    brit
    0.23
    çĸij
    0.23
    Activations Density 0.491%

    No Known Activations

    This feature has no known activations.