© 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. 41705
    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
     bids
    -0.27
    egra
    -0.27
    çľģæķĻèĤ²
    -0.26
    æķĪ
    -0.25
     realize
    -0.25
    scribe
    -0.24
    ias
    -0.24
    ENDER
    -0.24
     capacity
    -0.24
     bid
    -0.23
    POSITIVE LOGITS
    reur
    0.31
    ↵     ↵
    0.30
    mutable
    0.26
    é¦ĸ饰
    0.26
    çİĭèĢħ
    0.25
    âĢ¦↵↵↵
    0.25
    âĢ¦)↵↵
    0.25
    ador
    0.24
    air
    0.24
    âĢ¦↵
    0.24
    Activations Density 2.035%

    No Known Activations

    This feature has no known activations.