© 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. 107060
    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
    èĥĨ
    -0.30
    /css
    -0.29
     baÅŁÄ±na
    -0.27
    æ·ĺ
    -0.26
    åĨ»
    -0.26
    çļĦå¿ĥ
    -0.26
     heads
    -0.26
    oga
    -0.25
    åºļ
    -0.25
    IPH
    -0.24
    POSITIVE LOGITS
    å¼ĢéŨ
    0.28
     Contributors
    0.26
    æķŀå¼Ģ
    0.25
     flyer
    0.24
    æ½²
    0.24
    åĪĨæķ°
    0.24
    uitive
    0.23
    æ»ŀåIJİ
    0.23
    ungalow
    0.23
    ä¾Ľç»Ļ侧
    0.23
    Activations Density 3.038%

    No Known Activations

    This feature has no known activations.