© 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. 129683
    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
    specific
    -0.27
     fences
    -0.26
    çīĪ
    -0.25
    å½¢å¼ı
    -0.25
    osex
    -0.25
    SPA
    -0.24
    TAIL
    -0.24
    èĪŀè¹Ī
    -0.24
    olars
    -0.24
     supplied
    -0.24
    POSITIVE LOGITS
    ulant
    0.29
    åŁĶ
    0.27
    ption
    0.25
    synthesize
    0.24
    çģŃ
    0.23
     cá
    0.23
    ;)
    0.23
    (TM
    0.23
    åĸµ
    0.22
     synth
    0.22
    Activations Density 0.059%

    No Known Activations

    This feature has no known activations.