© 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. 88421
    Prev
    Next
    INDEX
    Explanations

    varied topics including "American"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     stakes
    -0.30
    _BUFF
    -0.26
     interpol
    -0.26
     zs
    -0.25
     straw
    -0.25
     wrists
    -0.25
     Enough
    -0.24
    çĩİ
    -0.24
    sez
    -0.24
    .dump
    -0.24
    POSITIVE LOGITS
    æĬķåħ¥
    0.27
    ogan
    0.26
    æ¼ĵ
    0.26
     peÅĤ
    0.26
     ord
    0.26
    InvalidArgumentException
    0.25
     g
    0.24
     hver
    0.24
    为主çļĦ
    0.24
    æ²»å®ī
    0.24
    Activations Density 8.938%

    No Known Activations