© 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. 88320
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
     depreci
    -0.28
     Nan
    -0.26
     underst
    -0.25
    èĢģçĪ·
    -0.25
     Albuquerque
    -0.25
    å¸IJ
    -0.24
    æľºåĻ¨
    -0.24
     part
    -0.24
     parliament
    -0.24
     Shades
    -0.23
    POSITIVE LOGITS
    =center
    0.25
    å°½
    0.24
    æĪijæĬĬ
    0.24
    çIJĨæĥ³çļĦ
    0.24
    çįIJ
    0.24
    åľºæĻ¯
    0.23
    fillType
    0.23
    .ObjectModel
    0.23
    resume
    0.23
    cling
    0.23
    Activations Density 1.975%

    No Known Activations