© 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. 18-TRANSCODER-HP
    7. 88450
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬŁ
    -0.32
    åıĭåĸĦ
    -0.28
    ä½İä½į
    -0.25
    æµĶ
    -0.25
    ton
    -0.25
    .cy
    -0.24
    sec
    -0.24
    èķĥ
    -0.24
    æ¸Ķ
    -0.24
    att
    -0.23
    POSITIVE LOGITS
    iculos
    0.27
    èµī
    0.26
     Viol
    0.26
     Ernst
    0.25
    çĤ¯
    0.24
    æĿ¡
    0.24
    à¹īาย
    0.24
    å¾ĹåĪĨ
    0.24
    å¼Ģåĩº
    0.23
    åĥĸ
    0.23
    Activations Density 0.102%

    No Known Activations

    This feature has no known activations.