© 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. 107694
    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
    æĻ®
    -0.30
     quadrant
    -0.27
    èĩªçĶ±
    -0.27
    icals
    -0.26
    ADING
    -0.26
    itur
    -0.26
    弧
    -0.26
    rup
    -0.26
    initialize
    -0.26
     thu
    -0.25
    POSITIVE LOGITS
    çļĦåīįæıIJ
    0.29
    tes
    0.28
     sufferers
    0.27
    çĵ¶é¢Ī
    0.27
    æĤ£æľī
    0.27
     holders
    0.26
    åīįæıIJæĺ¯
    0.26
     resist
    0.25
    Whilst
    0.25
    صÙĬب
    0.25
    Activations Density 20.322%

    No Known Activations

    This feature has no known activations.