© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39986
    Prev
    Next
    INDEX
    Explanations

    encryption

    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
    ucken
    -0.28
    _hooks
    -0.26
    oui
    -0.26
     oz
    -0.25
    (each
    -0.24
    麻
    -0.24
    apa
    -0.24
    arez
    -0.24
     Rev
    -0.24
     separate
    -0.23
    POSITIVE LOGITS
     orgy
    0.27
    ÙħÙĪ
    0.27
    nome
    0.26
    ãĤ«ãĥª
    0.25
    orget
    0.25
    åıªæĺ¯ä¸ºäºĨ
    0.25
    ylie
    0.25
    plat
    0.24
    emy
    0.23
    uelle
    0.23
    Activations Density 0.218%

    No Known Activations