© 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. 40126
    Prev
    Next
    INDEX
    Explanations

    code, numbers, error messages

    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
    çĮª
    -0.27
    reh
    -0.27
     specials
    -0.25
    ä¸İä¼Ĺä¸įåIJĮ
    -0.25
    short
    -0.25
     halluc
    -0.24
    localStorage
    -0.24
    æĹŃ
    -0.24
     special
    -0.23
     East
    -0.23
    POSITIVE LOGITS
    ób
    0.29
    御
    0.28
    hw
    0.26
    NEY
    0.25
    ioned
    0.25
    ãĥį
    0.24
    iad
    0.24
    ówn
    0.24
    ará
    0.24
    为ä¸ŃåĽ½
    0.23
    Activations Density 4.338%

    No Known Activations