© 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. 22-TRANSCODER-HP
    7. 88678
    Prev
    Next
    INDEX
    Explanations

    function words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XOR
    -0.27
    rier
    -0.24
    adder
    -0.24
     Sadd
    -0.24
     Belgi
    -0.23
    è¯Ħ级
    -0.23
    rage
    -0.22
     ^
    -0.22
    ensation
    -0.22
    .throw
    -0.22
    POSITIVE LOGITS
    ียว
    0.26
    illian
    0.24
     compl
    0.24
    ilian
    0.23
    åĨĪ
    0.23
    ä¸Ģ群
    0.23
    -capital
    0.23
    ä¹Łæĺ¯ä¸Ģ个
    0.23
    und
    0.22
    å´
    0.22
    Activations Density 0.001%

    No Known Activations