© 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. 39541
    Prev
    Next
    INDEX
    Explanations

    Words ending in "en"

    np_max-act · gemini-2.0-flash
    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
    çļĦæĺ¯
    -0.28
    åľ¨æĪijçļĦ
    -0.27
    _Syntax
    -0.27
     til
    -0.26
    æľĽ
    -0.26
    [X
    -0.26
    ìĬ¬
    -0.24
    lish
    -0.24
    为空
    -0.24
    çĻ½é¢Ĩ
    -0.24
    POSITIVE LOGITS
    ORN
    0.35
    SSIP
    0.28
    ParameterValue
    0.28
     roma
    0.27
     sinks
    0.26
    âĮł
    0.26
    loser
    0.26
    utters
    0.25
    orn
    0.25
     duties
    0.25
    Activations Density 2.280%

    No Known Activations