© 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. 40472
    Prev
    Next
    INDEX
    Explanations

    Years (2014, 2019, 2020)

    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
    说åĩº
    -0.25
    ãģĦãģ¡
    -0.24
    InstanceState
    -0.24
     arena
    -0.24
    管çIJĨå·¥ä½ľ
    -0.24
    éĵģ
    -0.23
     nostr
    -0.23
     trials
    -0.23
    èĤ±
    -0.23
     numbered
    -0.23
    POSITIVE LOGITS
    kart
    0.39
    Kn
    0.28
     MPs
    0.26
    å¢ŀèĩ³
    0.26
    reed
    0.25
    een
    0.25
    hev
    0.24
    èĥĸ
    0.24
    eenth
    0.24
     kart
    0.23
    Activations Density 0.408%

    No Known Activations