© 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. 130746
    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
    ä¹ĭä¸Ģ
    -0.28
     resp
    -0.28
    æģ°å¥½
    -0.26
    taire
    -0.26
     ce
    -0.24
     tel
    -0.24
    eto
    -0.24
    erm
    -0.24
    ives
    -0.24
    ä¸ĢåĪĻ
    -0.24
    POSITIVE LOGITS
    ä¸Ńåħ³
    0.26
     Downing
    0.26
    è´¸
    0.25
    å»ī
    0.24
    wis
    0.24
    èĩªåľ¨
    0.24
    ÃľN
    0.24
    -na
    0.23
    TIM
    0.23
     каждÑĭй
    0.23
    Activations Density 23.737%

    No Known Activations

    This feature has no known activations.