© 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. 89974
    Prev
    Next
    INDEX
    Explanations

    News article snippets

    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
     Inspector
    -0.28
    éĹ®é¢ĺæĺ¯
    -0.27
    zek
    -0.26
    baugh
    -0.26
    æĪªæŃ¢
    -0.26
    .mo
    -0.25
     reveal
    -0.25
    =end
    -0.25
    umo
    -0.24
    peq
    -0.24
    POSITIVE LOGITS
     Philosoph
    0.25
    çĺĽ
    0.24
    experiment
    0.23
    åĪ¹è½¦
    0.23
    éĿĻçĶµ
    0.23
    unding
    0.23
    timing
    0.23
    æħ¢æħ¢çļĦ
    0.23
    employ
    0.23
    åĵ²åѦ
    0.23
    Activations Density 5.954%

    No Known Activations