© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
     touch
    -0.56
    触
    -0.54
     touched
    -0.53
     touches
    -0.52
     Touch
    -0.49
     touching
    -0.49
    触æij¸
    -0.48
     tactile
    -0.45
    Touch
    -0.45
    Touches
    -0.43
    POSITIVE LOGITS
    æĦı大
    0.29
    éĩijåŃĹå¡Ķ
    0.28
    çıŃ
    0.27
    gst
    0.26
    æķĿ
    0.26
    èĬ±
    0.26
    çīĮçħ§
    0.25
    chein
    0.24
    çł
    0.24
    æľĪ亮
    0.24
    Activations Density 0.007%

    No Known Activations