© 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. 35-TRANSCODER-HP
    7. 38541
    Prev
    Next
    INDEX
    Explanations

    endings: "ester" or "est"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¦ĤæĦı
    -0.33
    èīº
    -0.26
    succ
    -0.26
    .lv
    -0.25
    ä¿Ĺè¯Ŀ说
    -0.25
    å¥Ĺ
    -0.25
     Gä
    -0.25
    dão
    -0.25
     myfile
    -0.24
    foods
    -0.24
    POSITIVE LOGITS
    ester
    0.36
    este
    0.29
    esto
    0.28
     purpose
    0.27
    inger
    0.26
     estimation
    0.26
    aper
    0.25
     Est
    0.25
    agher
    0.25
    stry
    0.25
    Activations Density 30.604%

    No Known Activations