© 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. 39619
    Prev
    Next
    INDEX
    Explanations

    software and computer code

    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
    laces
    -0.29
    __;↵
    -0.27
    åħĥå®Ŀ
    -0.26
    åĹħ
    -0.26
    æݨ广åºĶçĶ¨
    -0.25
    (TM
    -0.25
    __;
    -0.24
    aces
    -0.24
    å®Ŀè´µçļĦ
    -0.24
    StringValue
    -0.24
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.30
    ç£ģ
    0.27
    å¤ĦåĪĨ
    0.27
     False
    0.26
     settled
    0.26
    åIJ¸æĶ¶
    0.24
    åĪĴ
    0.24
    积水
    0.24
    ç¬ķ
    0.24
     exit
    0.24
    Activations Density 1.088%

    No Known Activations