© 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. 12-TRANSCODER-HP
    7. 23226
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æµİåįĹå¸Ĥ
    -0.27
    lia
    -0.27
    вÑĪ
    -0.26
    sher
    -0.25
    pile
    -0.25
     Bundle
    -0.25
    Disk
    -0.25
    shire
    -0.24
    bew
    -0.24
     #:
    -0.24
    POSITIVE LOGITS
     corruption
    0.27
    æµĬ
    0.26
    èĭ¥æĤ¨
    0.25
    çݯå¢ĥ污æŁĵ
    0.24
     hus
    0.24
     atmospheric
    0.24
    ropping
    0.23
    åݲ
    0.23
    chan
    0.23
     plotting
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.