© 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. 12-TRANSCODER-HP
    7. 23674
    Prev
    Next
    INDEX
    Explanations

    cardio, aortic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tal
    -0.28
    ä»ĵåĤ¨
    -0.27
    éĩijåĪļ
    -0.27
     weed
    -0.26
    .getItem
    -0.26
     Weed
    -0.26
    åģľè½¦ä½į
    -0.26
     Erf
    -0.26
     tumble
    -0.25
    游åĩ»
    -0.25
    POSITIVE LOGITS
    å¿ĥè¡Ģ管
    0.36
     Cardio
    0.32
    å¿ĥèĦı
    0.32
    å¿ĥè·³
    0.32
     arteries
    0.31
    é«ĺåİĭ
    0.29
    å¿ĥåĬ¨
    0.29
     vessels
    0.29
     Heart
    0.29
     ssl
    0.29
    Activations Density 0.036%

    No Known Activations