© 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. 12-TRANSCODER-HP
    7. 22045
    Prev
    Next
    INDEX
    Explanations

    Scraped internet text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ao
    -0.28
    çĨŁæĤīçļĦ
    -0.27
    gps
    -0.27
     organisation
    -0.27
    %-
    -0.25
    ä¹Łå¸ĮæľĽ
    -0.25
    ako
    -0.25
     sponsored
    -0.25
    idades
    -0.25
    åĶ¾
    -0.24
    POSITIVE LOGITS
    .prot
    0.27
    èĥº
    0.25
    regex
    0.24
    otron
    0.24
    leÅŁ
    0.23
    lique
    0.23
     disc
    0.23
    layui
    0.23
    實éļĽ
    0.23
     Vil
    0.23
    Activations Density 0.001%

    No Known Activations