© 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. 25592
    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
     cosy
    -0.29
    æľºä¼ļ
    -0.28
     nationally
    -0.28
    éŨæĪ·
    -0.27
    portlet
    -0.27
    GuidId
    -0.27
    /cms
    -0.27
     handleClick
    -0.27
     innocent
    -0.26
    estre
    -0.26
    POSITIVE LOGITS
    0.34
     U
    0.34
    :
    0.33
     Media
    0.33
    u
    0.32
     B
    0.31
    >
    0.31
     Long
    0.31
    Or
    0.31
    +
    0.31
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.