© 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. 30-TRANSCODER-HP
    7. 97115
    Prev
    Next
    INDEX
    Explanations

    technical/business texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sac
    -0.27
     ÑĩаÑģÑĤ
    -0.26
    Sac
    -0.26
    å±ħ
    -0.25
     sacrifice
    -0.25
    岬
    -0.25
    estre
    -0.25
     falling
    -0.24
     breadcrumbs
    -0.24
    ä¸ĢåIJį
    -0.24
    POSITIVE LOGITS
    .ravel
    0.28
    .wrap
    0.28
    æĸĩåĮĸçļĦ
    0.27
    çľĭä¸Ĭåİ»
    0.26
    ç¼ł
    0.26
    æĸĩåĮĸ
    0.26
    碣
    0.25
    æĭ´
    0.25
    oteric
    0.24
    terior
    0.24
    Activations Density 0.882%

    No Known Activations