© 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. 141639
    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
     guided
    -0.30
    INGER
    -0.28
    hq
    -0.28
    éĩįè¦ģåĨħ容
    -0.28
     maternal
    -0.28
    inger
    -0.26
    æĿ¥ä¸įåıĬ
    -0.26
    ante
    -0.26
     served
    -0.25
    èĮĥ
    -0.25
    POSITIVE LOGITS
    å¹´çĶ±
    0.25
    #SBATCH
    0.25
    Owners
    0.24
    ÙĪØ«
    0.24
     hart
    0.24
    \Support
    0.24
    客æĪ·æıIJä¾Ľ
    0.24
    มหา
    0.24
    prises
    0.23
     Owners
    0.23
    Activations Density 0.405%

    No Known Activations

    This feature has no known activations.