© 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. 86840
    Prev
    Next
    INDEX
    Explanations

    Advantages and disadvantages

    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
    Negative Logits
    Rnd
    -0.26
     McCorm
    -0.26
    UTION
    -0.26
     Manitoba
    -0.24
    ç¡ķ士åѦä½į
    -0.24
     Shotgun
    -0.24
    ä¸ªå·¥ä½ľæĹ¥
    -0.24
    abd
    -0.23
    (Method
    -0.23
     Measure
    -0.23
    POSITIVE LOGITS
    usan
    0.27
    æ´¾
    0.27
    ä¾£
    0.27
    sist
    0.26
    sse
    0.26
    æ»ŀ
    0.26
    éģĵçIJĨ
    0.26
    ây
    0.25
    .Persistence
    0.25
     EVERY
    0.25
    Activations Density 0.008%

    No Known Activations