© 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. 97295
    Prev
    Next
    INDEX
    Explanations

    Places

    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
    onde
    -0.27
    éĥĬ
    -0.26
     where
    -0.26
     masks
    -0.26
     exposure
    -0.25
     mask
    -0.25
     Import
    -0.25
     ser
    -0.25
    ¬´
    -0.25
     something
    -0.25
    POSITIVE LOGITS
    velt
    0.28
    大家ä¸Ģèµ·
    0.26
     hut
    0.26
    è´µ
    0.24
    owler
    0.24
     Happ
    0.24
    æĬĬæĮģ
    0.24
     bande
    0.24
    thouse
    0.24
    itsu
    0.23
    Activations Density 0.011%

    No Known Activations