© 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. 63046
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     transfer
    -0.32
    tras
    -0.28
    ekyll
    -0.27
     Transfer
    -0.26
    åĨ³
    -0.25
    ä¸įåľ¨ä¹İ
    -0.25
     formulation
    -0.24
    å¼ıçļĦ
    -0.24
    leigh
    -0.24
    iami
    -0.24
    POSITIVE LOGITS
    çĪª
    0.29
    éķĸ
    0.29
    æīĵçĮİ
    0.27
    OLA
    0.26
    htable
    0.26
    áb
    0.26
    OLE
    0.25
    osite
    0.25
    quelle
    0.24
    æ¡Įä¸Ĭ
    0.24
    Activations Density 21.323%

    No Known Activations

    This feature has no known activations.