© 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. 25251
    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
    Not in Any Lists

    No Comments

    Negative Logits
     project
    -0.28
     later
    -0.26
     bip
    -0.26
     defined
    -0.26
     Solid
    -0.26
    ä¸ĥæľĪ
    -0.25
     [{
    -0.25
     Sink
    -0.25
     vulnerability
    -0.25
     Mo
    -0.24
    POSITIVE LOGITS
    utan
    0.30
    ylon
    0.27
    plode
    0.27
    çļĦèµĦéĩij
    0.27
    minster
    0.27
    uent
    0.27
    æĿ¼
    0.25
    ounters
    0.25
    èĻ¢
    0.25
    æĹ¥åĨħ
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.