© 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. 56423
    Prev
    Next
    INDEX
    Explanations

    Non-English or code

    np_max-act-logits · gemini-2.0-flash
    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
    unc
    -0.29
     scares
    -0.27
     unc
    -0.26
    imson
    -0.26
    ç³Ļ
    -0.26
    ir
    -0.26
     unfamiliar
    -0.25
     Interior
    -0.24
     incorporation
    -0.24
     unf
    -0.24
    POSITIVE LOGITS
    ç½²
    0.27
    åij¨ä¸Ģ
    0.27
    ULAR
    0.27
    rib
    0.26
     parliamentary
    0.25
    blockquote
    0.25
    çļĦ第ä¸Ģ个
    0.25
    第ä¸Ģ
    0.24
    第ä¸Ģ个
    0.24
    .mit
    0.24
    Activations Density 0.002%

    No Known Activations