© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25474
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    槽
    -0.27
    ÑĥÑĢÑģ
    -0.24
    ady
    -0.24
    对ä¸ŃåĽ½
    -0.24
    Baby
    -0.24
    fdc
    -0.24
    cept
    -0.23
    .Brand
    -0.23
    åĵģçīĮçļĦ
    -0.23
    æįº
    -0.23
    POSITIVE LOGITS
     Rai
    0.25
     signatures
    0.24
    ve
    0.23
    åīįéĿ¢
    0.23
    igation
    0.23
    ilda
    0.23
    stery
    0.23
    ibold
    0.23
     bets
    0.22
    ="↵
    0.22
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.