© 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. 113073
    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
    íķĢ
    -0.24
    -awesome
    -0.24
    ersive
    -0.24
    editary
    -0.23
    leted
    -0.23
     incremental
    -0.23
     rút
    -0.22
    illary
    -0.22
    phia
    -0.22
     underst
    -0.22
    POSITIVE LOGITS
    çļĦåĨ³å¿ĥ
    0.26
    æĦŁè§īåĪ°
    0.25
     Inside
    0.24
    rays
    0.24
     Distance
    0.23
    imity
    0.23
    æĽ³
    0.23
    æĭĸ
    0.22
     chance
    0.22
    tera
    0.22
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.