© 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. 97138
    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
    Negative Logits
    aed
    -0.30
    clist
    -0.27
    åįĹåĮĹ
    -0.27
    README
    -0.27
     paused
    -0.26
    paused
    -0.26
    Opens
    -0.25
    _framework
    -0.25
    ilage
    -0.25
    .lift
    -0.25
    POSITIVE LOGITS
    V
    0.28
    æ¡£
    0.27
     поÑĤ
    0.27
    v
    0.27
    æķıæĦŁ
    0.26
     Warning
    0.26
    uz
    0.25
    ÑĥÑģ
    0.25
    DD
    0.25
    ikers
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.