© 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. 88116
    Prev
    Next
    INDEX
    Explanations

    technical writing/computer code

    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
    strand
    -0.28
     peer
    -0.27
     navigator
    -0.26
    éĥİ
    -0.25
    navigator
    -0.24
    åıĤ
    -0.23
    (axis
    -0.23
     Grade
    -0.23
     unload
    -0.23
    æ´§
    -0.23
    POSITIVE LOGITS
    çĶ»éĿ¢
    0.33
     Integral
    0.29
    cker
    0.28
    çļĦçĶ»éĿ¢
    0.26
     pockets
    0.26
    åħ³åĪĩ
    0.25
    uet
    0.25
     Interview
    0.25
    åħ¼é¡¾
    0.25
    åľĨå½¢
    0.25
    Activations Density 2.550%

    No Known Activations