© 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. 39771
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    еÑĨ
    -0.27
    ||(
    -0.27
     amusing
    -0.26
     (),↵
    -0.26
    ascar
    -0.26
    quee
    -0.26
    èĬĿ麻
    -0.26
    ÑĨов
    -0.25
    åįĬ个
    -0.25
    );*/↵
    -0.25
    POSITIVE LOGITS
    éĽĨä½ĵ
    0.26
     ded
    0.26
    综åIJĪä½ĵ
    0.25
    çŃ¹çłģ
    0.25
    -Identifier
    0.24
    roph
    0.23
    丸
    0.23
    .PARAM
    0.23
    	ROM
    0.23
     Jennings
    0.23
    Activations Density 0.859%

    No Known Activations