© 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. 27-TRANSCODER-HP
    7. 7833
    Prev
    Next
    INDEX
    Explanations

    say "'d" or "would"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    оÑģÑĮ
    -0.28
    æĽ¦
    -0.26
    æĥħ趣
    -0.26
     Crown
    -0.26
    omatic
    -0.26
    lice
    -0.26
    typ
    -0.25
     hypoth
    -0.25
    伦
    -0.25
    女åĦ¿
    -0.25
    POSITIVE LOGITS
    ousy
    0.27
    ä¼ļéķ¿
    0.27
    cks
    0.25
    èĤļåŃIJ
    0.25
     mouths
    0.25
    cards
    0.24
    Much
    0.24
    åįļ客
    0.24
    æĽ´è¦ģ
    0.23
    æĹ¢
    0.23
    Activations Density 0.001%

    No Known Activations