© 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. 41016
    Prev
    Next
    INDEX
    Explanations

    medicine/healthcare

    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
    ìĿµ
    -0.26
    buzz
    -0.25
    +"]
    -0.25
    ège
    -0.25
    è¿Ń
    -0.25
     rebuilt
    -0.24
    æĬ¥å¤į
    -0.24
    +_
    -0.23
     peeled
    -0.23
     _$
    -0.23
    POSITIVE LOGITS
    çij
    0.29
    orsch
    0.28
    沿
    0.28
    ication
    0.28
    -driving
    0.25
    ysz
    0.25
     reg
    0.25
    ance
    0.25
    驾驶
    0.24
     Pro
    0.24
    Activations Density 0.662%

    No Known Activations