© 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. 142103
    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
     l
    -0.29
     multip
    -0.28
     rel
    -0.28
     cosmetic
    -0.28
     turn
    -0.27
     serious
    -0.26
     variant
    -0.26
     stroke
    -0.26
     extr
    -0.26
     traveling
    -0.26
    POSITIVE LOGITS
     undisclosed
    0.30
    dna
    0.30
    -align
    0.28
    éŀ
    0.28
    çīĪ
    0.27
    Binding
    0.27
     поб
    0.26
    Pager
    0.24
    ixer
    0.24
    encies
    0.24
    Activations Density 3.436%

    No Known Activations

    This feature has no known activations.