© 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. 142394
    Prev
    Next
    INDEX
    Explanations

    confusion

    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
    äºĮæīĭ
    -0.27
    avery
    -0.27
    ä¸Ģ份
    -0.26
    áŀİ
    -0.25
     tow
    -0.25
     Affero
    -0.25
    ä¸Ģæīĭ
    -0.25
     Secondary
    -0.24
    ä¸įæĺİçĻ½
    -0.24
    onet
    -0.24
    POSITIVE LOGITS
     purpose
    0.28
    èĩ¨
    0.28
    Purpose
    0.27
     purposes
    0.26
     Purpose
    0.25
     fiz
    0.25
    åģĪ
    0.25
    ç°§
    0.25
    çĹħåĽł
    0.25
     admitting
    0.24
    Activations Density 10.667%

    No Known Activations