© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129374
    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
    agens
    -0.33
    izzard
    -0.27
    ere
    -0.26
     ade
    -0.25
     spelling
    -0.25
    è¿İ
    -0.24
     Resorts
    -0.24
    èĨĿ
    -0.24
    pell
    -0.24
    ,:,
    -0.24
    POSITIVE LOGITS
    çī¹æ´¾
    0.29
     beating
    0.26
    CDATA
    0.26
    Dou
    0.25
    IFICATE
    0.25
    ä¸ĵæłı
    0.25
     Doug
    0.25
    oit
    0.24
    æīŃ
    0.24
    acl
    0.24
    Activations Density 10.425%

    No Known Activations

    This feature has no known activations.