© 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. 108160
    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
    èĢĮ对äºİ
    -0.31
    ä½Ĩæĺ¯å¯¹äºİ
    -0.28
    ä½Ĩ对äºİ
    -0.28
    ä¿¡æģ¯æľįåĬ¡
    -0.28
     inflamm
    -0.27
    å·½
    -0.26
    \Helper
    -0.26
    FormGroup
    -0.25
    ÐĤ
    -0.25
    èĢĮè¿Ļ
    -0.25
    POSITIVE LOGITS
    ote
    0.27
     Conduct
    0.27
    åŀ¦
    0.25
     Clock
    0.25
    âte
    0.25
    ipay
    0.24
    elerik
    0.24
    ãĤį
    0.24
     override
    0.23
    imony
    0.23
    Activations Density 1.106%

    No Known Activations

    This feature has no known activations.