© 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. 141090
    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
    åľ°æłĩ
    -0.29
    ¦Ĥ
    -0.26
    澳大
    -0.26
    aseline
    -0.26
    ä¹ŁåºĶ该
    -0.25
    ä¸Ńä»ĭ
    -0.25
    æłĩå¿Ĺ
    -0.25
    ä¸Ģèĩ´æĢ§
    -0.25
     newfound
    -0.25
    xaf
    -0.25
    POSITIVE LOGITS
    åĬ²
    0.27
    cp
    0.27
    .DIS
    0.26
    oll
    0.25
    ollen
    0.24
    ç¥ī
    0.24
    à¤Ŀ
    0.24
    精彩çļĦ
    0.23
    Ľå»º
    0.23
    å¿ĺ
    0.23
    Activations Density 6.774%

    No Known Activations

    This feature has no known activations.