© 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. 9767
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ingleton
    -0.33
    éĺ´
    -0.29
    æĿĢ
    -0.27
     Rhodes
    -0.25
     asyncio
    -0.25
    çĶŁæ´»çݯå¢ĥ
    -0.25
    æķıæĦŁ
    -0.25
    edo
    -0.24
    ä½ı
    -0.24
     Point
    -0.24
    POSITIVE LOGITS
    mah
    0.27
    bert
    0.26
    kiego
    0.25
    subj
    0.25
    okie
    0.25
    ä¸Ģ线
    0.25
    kie
    0.24
    ucht
    0.24
    etxt
    0.23
    erez
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.