© 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. 86943
    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
     représ
    -0.28
     _:
    -0.26
     _______,
    -0.25
    }):
    -0.23
     Kou
    -0.23
     shock
    -0.23
     nominate
    -0.23
    remen
    -0.23
    Terms
    -0.23
    æĽ´è¦ģ
    -0.23
    POSITIVE LOGITS
     existence
    0.27
    éĺ²åį«
    0.25
    own
    0.24
     adequ
    0.24
     past
    0.24
     physical
    0.23
     cul
    0.23
    .binding
    0.23
    çļĦåĬªåĬĽ
    0.23
    æĪijçĽ¸ä¿¡
    0.22
    Activations Density 0.195%

    No Known Activations

    This feature has no known activations.