© 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. 64636
    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
    Negative Logits
    è¡ħ
    -0.30
     expanding
    -0.26
    oldem
    -0.26
     transports
    -0.25
     disposed
    -0.25
    kip
    -0.25
    ä¸įæĸŃæī©å¤§
    -0.25
    casting
    -0.24
    ondo
    -0.24
    ળ
    -0.24
    POSITIVE LOGITS
    éĹŃ
    0.27
    å¯Ĵ
    0.26
    anness
    0.26
    å¯ĮåĬĽ
    0.26
    æĹ¶ä»£ä¸ŃåĽ½
    0.25
     presence
    0.24
    æ¦Ĥ念
    0.24
    ception
    0.24
    pline
    0.24
    ':''
    0.24
    Activations Density 9.213%

    No Known Activations

    This feature has no known activations.