© 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. 62861
    Prev
    Next
    INDEX
    Explanations

    eco-friendly

    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
    æ·³
    -0.29
    èĽ¾
    -0.28
     chuyá»ĩn
    -0.27
    룩
    -0.26
     ashamed
    -0.25
     tÆ°
    -0.25
    urers
    -0.24
     höher
    -0.24
    istry
    -0.24
    anking
    -0.24
    POSITIVE LOGITS
    æݥ触
    0.26
    ä¸įåIJĮç±»åŀĭ
    0.25
    ä¸įåIJĮç¨ĭ度
    0.25
    arms
    0.25
     tact
    0.25
    èķĹ
    0.24
    afort
    0.24
     touch
    0.24
    acock
    0.24
     facto
    0.24
    Activations Density 12.523%

    No Known Activations