© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97779
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     mort
    -0.26
    MAT
    -0.26
    mat
    -0.25
     Boundary
    -0.24
    æĢ§è´¨
    -0.24
    è¾ĥä½İ
    -0.24
    fall
    -0.24
     اÙĦÙħتØŃدة
    -0.24
    adel
    -0.23
    technical
    -0.23
    POSITIVE LOGITS
    è°¬
    0.31
    QRS
    0.30
    è£Ļ
    0.27
    nex
    0.27
    ä¸Ģç§Ĵ
    0.27
    lices
    0.26
    使çĶ¨èĢħæĪĸ
    0.26
    è¿ĻåIJį
    0.25
     excel
    0.24
    ieres
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.