© 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. 32-TRANSCODER-HP
    7. 43628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -0.34
    第äºĶ
    -0.32
    çļĦä¸įåIJĮ
    -0.32
    0
    -0.30
    第ä¸Ģ
    -0.30
    6
    -0.29
    4
    -0.28
    7
    -0.28
    8
    -0.28
     fifth
    -0.28
    POSITIVE LOGITS
    annie
    0.28
    unate
    0.26
    arse
    0.25
    ailable
    0.25
    éĩįå·¥
    0.24
    ,application
    0.24
    .dm
    0.24
    åħľ
    0.24
    idable
    0.24
    ElementException
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.