© 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. 32-TRANSCODER-HP
    7. 43966
    Prev
    Next
    INDEX
    Explanations

    ro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sand
    -0.26
    irector
    -0.25
    eden
    -0.25
     sap
    -0.25
     money
    -0.25
     off
    -0.24
    ycz
    -0.24
    etas
    -0.24
    ï½į
    -0.24
     hous
    -0.24
    POSITIVE LOGITS
    lid
    0.30
    fl
    0.28
     Flavor
    0.26
     plc
    0.26
    æ°Ľ
    0.26
     flavour
    0.25
    acity
    0.25
    Fl
    0.25
    空æ°Ķè´¨éĩı
    0.24
    åħĪæĬĬ
    0.24
    Activations Density 0.004%

    No Known Activations