© 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. 129555
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    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
    esis
    -0.28
    subclass
    -0.27
     Innoc
    -0.26
    åĩ«
    -0.25
     grade
    -0.24
     Thesis
    -0.24
    kar
    -0.24
    shine
    -0.24
    ive
    -0.24
     UserRole
    -0.24
    POSITIVE LOGITS
    带åĽŀ
    0.28
     revealed
    0.28
    åı¯ä»¥æĽ´å¥½
    0.27
    æīĭä¸ŃçļĦ
    0.26
    dea
    0.26
     spotting
    0.26
    IDL
    0.26
     agenda
    0.25
    带åĪ°
    0.25
    REW
    0.25
    Activations Density 3.044%

    No Known Activations