© 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. 17881
    Prev
    Next
    INDEX
    Explanations

    Irish 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
     coll
    -0.29
    PAD
    -0.27
     Gr
    -0.27
     Coll
    -0.27
     jump
    -0.26
    eliness
    -0.26
     Prote
    -0.25
     home
    -0.25
     collateral
    -0.25
    å¹³å®ī
    -0.25
    POSITIVE LOGITS
    bart
    0.26
    chest
    0.26
    itti
    0.26
    strand
    0.25
    补水
    0.25
    quartered
    0.24
    aland
    0.24
    arts
    0.24
    ral
    0.24
    annis
    0.23
    Activations Density 0.125%

    No Known Activations