© 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. 25-TRANSCODER-HP
    7. 109454
    Prev
    Next
    INDEX
    Explanations

    unusual names or identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    quier
    -0.25
    .super
    -0.25
    pn
    -0.25
    éĢIJ
    -0.24
     atl
    -0.24
    arser
    -0.24
    åľ¨æĦı
    -0.23
    æ¸Ķ
    -0.23
    burgh
    -0.23
    quil
    -0.23
    POSITIVE LOGITS
    ses
    0.28
    iams
    0.27
    antt
    0.25
     Minist
    0.25
    稷
    0.24
    iant
    0.23
    REE
    0.23
    acha
    0.23
    contrib
    0.23
    KER
    0.23
    Activations Density 0.155%

    No Known Activations