© 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. 128994
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    kea
    -0.27
    .capture
    -0.25
    achs
    -0.25
    _rs
    -0.24
    stein
    -0.23
    .Tables
    -0.23
    æł¸å®ŀ
    -0.23
    +len
    -0.23
    erb
    -0.23
    Incre
    -0.23
    POSITIVE LOGITS
     what
    0.41
    what
    0.41
    ä½ķå¤Ħ
    0.41
    ä»Ģä¹Īåij¢
    0.39
    ä»Ģä¹Ī
    0.39
     What
    0.37
    What
    0.36
    æĺ¯ä»Ģä¹Ī
    0.34
    ä½ķ
    0.34
    .what
    0.34
    Activations Density 0.013%

    No Known Activations