© 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. 20-TRANSCODER-HP
    7. 142294
    Prev
    Next
    INDEX
    Explanations

    adapt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¥Ĺ
    -0.27
    ialis
    -0.26
     configs
    -0.25
    å·¥ä¸ļ
    -0.24
    updated
    -0.24
    inesis
    -0.24
     Su
    -0.23
    ylinder
    -0.23
    å¦Ĥæŀľä½ł
    -0.23
    大éĿ¢ç§¯
    -0.23
    POSITIVE LOGITS
     Crimea
    0.27
    ToDevice
    0.27
    .Raw
    0.26
    ToObject
    0.26
     UFC
    0.25
    éĿ¢åīį
    0.24
    äºĭåħĪ
    0.24
    oise
    0.24
     setDefaultCloseOperation
    0.23
    yle
    0.23
    Activations Density 8.343%

    No Known Activations