© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    Code/math special characters

    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
    [][
    -0.26
    éĹª
    -0.26
    cher
    -0.25
    Ñģов
    -0.25
     arcade
    -0.25
    æµ®
    -0.25
    arda
    -0.24
    ä»»ä½ķå½¢å¼ı
    -0.23
    loat
    -0.23
    å®Į
    -0.23
    POSITIVE LOGITS
    inet
    0.27
    zos
    0.26
     Governors
    0.26
    ç¥ī
    0.25
    .scalar
    0.24
     hospital
    0.24
    å«ģ
    0.23
    éªĭ
    0.23
    imu
    0.23
     ż
    0.22
    Activations Density 2.048%

    No Known Activations