© 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. 129252
    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
    ours
    -0.26
    erus
    -0.25
    cede
    -0.25
    _recursive
    -0.24
    abh
    -0.24
    Recursive
    -0.24
     dÄ±ÅŁÄ±
    -0.24
    æĸ¹æ³ķ
    -0.23
     drill
    -0.23
    terr
    -0.23
    POSITIVE LOGITS
    elm
    0.29
    ¦¬
    0.26
    渣
    0.26
    yclopedia
    0.25
    æĥº
    0.25
     mix
    0.25
     Saturn
    0.25
    oader
    0.24
    eed
    0.23
     Mixer
    0.23
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.