© 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. 64584
    Prev
    Next
    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    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
    tees
    -0.27
    ä¹ĭæīĢ
    -0.26
    çĸĸ
    -0.26
     Bear
    -0.25
    å¤ĸåĽ½äºº
    -0.25
     occasion
    -0.24
    tors
    -0.24
    âĪ¶
    -0.24
    occasion
    -0.24
    éĽĸ
    -0.24
    POSITIVE LOGITS
    mann
    0.30
    глав
    0.27
    lett
    0.26
    enticate
    0.25
    alem
    0.24
    uje
    0.24
    çĪĨ
    0.24
    大人
    0.24
    theless
    0.24
     QTest
    0.24
    Activations Density 11.448%

    No Known Activations