© 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. 14-TRANSCODER-HP
    7. 39418
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æħ¨
    -0.28
     er
    -0.27
     Green
    -0.25
    绿
    -0.25
    car
    -0.24
    åħµ
    -0.24
     Mississippi
    -0.24
    AILS
    -0.24
    SSL
    -0.24
    æĺı
    -0.24
    POSITIVE LOGITS
     sÆ°
    0.29
    åħ³éŨ
    0.28
    æľįåĬ¡ä½ĵç³»
    0.27
    plaint
    0.27
    osite
    0.27
     trib
    0.27
    Bear
    0.26
     dictatorship
    0.26
    osos
    0.26
    åIJł
    0.25
    Activations Density 3.781%

    No Known Activations

    This feature has no known activations.