© 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. 58487
    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
     wo
    -0.25
    ailed
    -0.25
     qualified
    -0.24
     Beste
    -0.23
     parallels
    -0.23
    áng
    -0.23
    ä¸Ģå¤Ħ
    -0.23
    ollah
    -0.23
     Broadcom
    -0.23
    ensing
    -0.23
    POSITIVE LOGITS
    itter
    0.28
    ity
    0.28
    ylinder
    0.27
    çľ¨çľ¼
    0.26
    ivity
    0.26
    åı¯çĪ±
    0.26
    iosa
    0.26
    gran
    0.25
    csi
    0.25
    ness
    0.24
    Activations Density 0.302%

    No Known Activations

    This feature has no known activations.