© 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. 131213
    Prev
    Next
    INDEX
    Explanations

    is, are

    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
    ç½Ħ
    -0.31
    æľīæĿĥ
    -0.28
     racked
    -0.28
    recent
    -0.27
    æłĩçļĦ
    -0.26
    çļĦæ¯ĶèµĽ
    -0.24
    Magnitude
    -0.23
    PTH
    -0.23
    æİĤ
    -0.23
    è´¨æĬ¼
    -0.23
    POSITIVE LOGITS
     crucial
    0.32
    尤为éĩįè¦ģ
    0.27
     complimentary
    0.27
     needed
    0.26
     necessary
    0.25
    éĹľéįµ
    0.25
     must
    0.25
     key
    0.25
    åħ¥
    0.25
     essential
    0.25
    Activations Density 0.018%

    No Known Activations