© 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. 62643
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
    Negative Logits
    çļĦåĽŀçŃĶ
    -0.31
    nar
    -0.29
    emouth
    -0.28
     pard
    -0.27
     nar
    -0.27
    à®±
    -0.26
    igans
    -0.26
    å¾Ĭ
    -0.26
    iral
    -0.25
    çļĦçŃĶæ¡Ī
    -0.25
    POSITIVE LOGITS
    ä¸Ģè½®
    0.30
    cient
    0.29
    ubi
    0.28
    è½®
    0.28
    sla
    0.27
    REA
    0.26
    uber
    0.26
    天天
    0.25
    reas
    0.25
    rott
    0.25
    Activations Density 1.208%

    No Known Activations