© 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. 52731
    Prev
    Next
    INDEX
    Explanations

    distant locations

    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
    ä¼ĺå¼Ĥ
    -0.31
    %X
    -0.29
     impeccable
    -0.27
     formidable
    -0.26
     decreasing
    -0.26
    åįĵè¶Ĭ
    -0.25
    /DD
    -0.25
     immense
    -0.25
     tremendous
    -0.25
     effortless
    -0.24
    POSITIVE LOGITS
     character
    0.34
     section
    0.32
     stretch
    0.31
     Ton
    0.30
     reaches
    0.29
    çļĦå¿ĥæĥħ
    0.28
     part
    0.27
     Yet
    0.27
     Reach
    0.27
     Said
    0.27
    Activations Density 0.024%

    No Known Activations