© 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. 9266
    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
     favor
    -0.27
     mastering
    -0.26
    favor
    -0.25
    _HandleTypeDef
    -0.25
    éĹª
    -0.25
     dread
    -0.24
    mailto
    -0.24
     Kind
    -0.24
     terrifying
    -0.24
    ihan
    -0.24
    POSITIVE LOGITS
    ÑĢÑİ
    0.27
    éĻĦ件
    0.27
    çĨĶ
    0.26
    ä¸Ńæĸ¹
    0.25
    woo
    0.25
    å¦ĩ
    0.25
    goog
    0.25
    RM
    0.24
    aggi
    0.24
    onia
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.