© 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. 110925
    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
    npos
    -0.30
    ServiceImpl
    -0.25
    edia
    -0.24
    ois
    -0.24
    alin
    -0.24
    onta
    -0.24
    æĢ§çļĦ
    -0.23
    çİ°å®ŀçĶŁæ´»
    -0.23
    cock
    -0.22
    _IMPORTED
    -0.22
    POSITIVE LOGITS
     För
    0.25
     claro
    0.24
    agers
    0.24
    åŃ£
    0.24
    ROLS
    0.23
     genders
    0.23
    ãģĬ客æ§ĺ
    0.23
     ea
    0.23
    ups
    0.23
    /ec
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.