© 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. 90332
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    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
    OI
    -0.28
     longitudinal
    -0.27
     trace
    -0.26
    andles
    -0.26
    DDL
    -0.26
     asympt
    -0.26
     characteristic
    -0.26
     bern
    -0.25
     facilit
    -0.25
     ÑģеÑĢ
    -0.25
    POSITIVE LOGITS
     junk
    0.29
    è´µ
    0.28
    âĸĮ
    0.28
    kd
    0.28
    kt
    0.27
    è²´
    0.26
    KIT
    0.26
    æĹłç¼ĺ
    0.26
    .|
    0.26
     flock
    0.26
    Activations Density 7.575%

    No Known Activations