© 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. 63312
    Prev
    Next
    INDEX
    Explanations

    lead/result

    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
     collectionView
    -0.27
    åijĨ
    -0.26
     depend
    -0.26
     baģlı
    -0.25
    å¾ĪæŃ£å¸¸
    -0.25
    ouver
    -0.24
    ,size
    -0.24
    )|(
    -0.24
    人工
    -0.24
     légère
    -0.24
    POSITIVE LOGITS
    é¢ľ
    0.27
     plunge
    0.27
    å¼ķèµ·äºĨ
    0.27
    apl
    0.26
     fem
    0.26
    为é¦ĸçļĦ
    0.25
    uish
    0.25
    ä¸ĢéŨ
    0.25
     leading
    0.25
    orum
    0.24
    Activations Density 12.239%

    No Known Activations