© 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. 56420
    Prev
    Next
    INDEX
    Explanations

    general concepts

    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
     pursued
    -0.29
    å½¢æĪIJçļĦ
    -0.27
     gotten
    -0.27
     formed
    -0.26
    åıĸå¾ĹäºĨ
    -0.26
    æľīå¾ħ
    -0.26
    å½¢æĪIJäºĨ
    -0.26
    å¾ĹåĪ°äºĨ
    -0.26
    adm
    -0.25
    ä¹°åĪ°
    -0.25
    POSITIVE LOGITS
     overt
    0.27
     shed
    0.27
    (chart
    0.26
     rightfully
    0.25
    çĺ¦èº«
    0.25
     actually
    0.24
    æĪijä»¬ä¹Ł
    0.24
     ent
    0.24
     oxid
    0.24
    æĪij们
    0.23
    Activations Density 0.008%

    No Known Activations