© 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. 129390
    Prev
    Next
    INDEX
    Explanations

    Random article beginnings

    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
    è½²
    -0.28
     #:
    -0.27
    æľĢ好ä¸įè¦ģ
    -0.27
     Ef
    -0.26
    åĿIJçĿĢ
    -0.26
     CallingConvention
    -0.25
    SizeMode
    -0.25
    ]._
    -0.25
     Owned
    -0.24
     owned
    -0.24
    POSITIVE LOGITS
     Gerry
    0.25
    etable
    0.25
    -project
    0.25
    hoot
    0.24
    oder
    0.24
     pred
    0.24
     meanwhile
    0.23
    ç³»
    0.23
    ouncements
    0.23
    gable
    0.23
    Activations Density 62.864%

    No Known Activations