© 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. 27-TRANSCODER-HP
    7. 56377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    able
    -0.26
    ÑĤай
    -0.26
    Invoker
    -0.26
    edException
    -0.25
     inv
    -0.24
    æµģéĢļ
    -0.24
    wright
    -0.24
    /down
    -0.24
    reau
    -0.24
    empo
    -0.24
    POSITIVE LOGITS
    ething
    0.28
     innocence
    0.28
    åĸĭ
    0.27
    atures
    0.26
    shaw
    0.24
    å°¼æĸ¯
    0.24
    ä¸Ģ头
    0.23
    arket
    0.23
    åīIJ
    0.23
    avn
    0.23
    Activations Density 1.070%

    No Known Activations

    This feature has no known activations.