© 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. 33-TRANSCODER-HP
    7. 54828
    Prev
    Next
    INDEX
    Explanations

    urban

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    计
    -0.33
    IJľ
    -0.29
    伯
    -0.28
     dich
    -0.27
    è¨Ī
    -0.27
    åİī
    -0.26
    eph
    -0.26
     di
    -0.26
     br
    -0.26
     drag
    -0.26
    POSITIVE LOGITS
    ossil
    0.27
    ä¹¡åľŁ
    0.26
     Ribbon
    0.26
    instrument
    0.26
    ä¹ĭ乡
    0.25
     bande
    0.24
    æĦıä¹īä¸ĬçļĦ
    0.24
     soils
    0.24
    åIJ¬è¯¾
    0.23
    å±ķåĮº
    0.23
    Activations Density 0.004%

    No Known Activations