© 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. 31-TRANSCODER-HP
    7. 17838
    Prev
    Next
    INDEX
    Explanations

    International business and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åįļçī©é¦Ĩ
    -0.32
    çĬ¶åħĥ
    -0.28
    uts
    -0.27
    .world
    -0.25
    dration
    -0.25
    åĽ½å®¶éĩįçĤ¹
    -0.24
    åħŃåIJĪ
    -0.24
     World
    -0.24
    ä¾Ŀ次
    -0.24
     world
    -0.24
    POSITIVE LOGITS
     operand
    0.30
     départ
    0.29
     territories
    0.29
    客
    0.28
     operations
    0.28
     опеÑĢ
    0.26
    abant
    0.25
    operations
    0.25
    rms
    0.25
    abet
    0.24
    Activations Density 0.008%

    No Known Activations