© 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. 33-TRANSCODER-HP
    7. 52504
    Prev
    Next
    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     wom
    -0.30
     fr
    -0.28
     annot
    -0.27
     fe
    -0.26
     pot
    -0.26
     marks
    -0.26
     deviation
    -0.25
    æī¶
    -0.25
     train
    -0.25
     ann
    -0.25
    POSITIVE LOGITS
    .CreateInstance
    0.27
    ç¨Ģ
    0.25
    ï¼ģ↵↵
    0.25
    MBER
    0.25
    æĹ¥æĬ¥ç¤¾
    0.25
    Gran
    0.25
    åĴ¬
    0.24
    avings
    0.24
    åĹª
    0.24
    çıł
    0.24
    Activations Density 0.107%

    No Known Activations