© 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. 39720
    Prev
    Next
    INDEX
    Explanations

    legal texts and names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    gems
    -0.26
    gon
    -0.26
    éħļ
    -0.25
    å¿ĥ缮ä¸Ń
    -0.24
     remodeling
    -0.24
    fen
    -0.24
    лен
    -0.24
     Died
    -0.23
    å¼
    -0.23
    -serving
    -0.23
    POSITIVE LOGITS
    ãĥIJãĥ¬
    0.26
    æĸ¹åIJij
    0.26
    citation
    0.25
     Glover
    0.25
    ismet
    0.24
    çī
    0.24
    è±¢
    0.24
     queryInterface
    0.23
    æŶ
    0.23
    CLI
    0.23
    Activations Density 1.085%

    No Known Activations