© 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. 52559
    Prev
    Next
    INDEX
    Explanations

    test

    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
    rove
    -0.28
    ãĥªãĥ³
    -0.28
     verk
    -0.24
    geh
    -0.24
    ä¹ĺ
    -0.24
     Proxy
    -0.24
    éĴĪ
    -0.24
    éĹ
    -0.24
    èĢ¿
    -0.23
     Brah
    -0.23
    POSITIVE LOGITS
    ano
    0.30
    æIJ¶
    0.29
    ificantly
    0.28
    äºĭ项
    0.28
     item
    0.28
    æĪij们ä¸Ģèµ·
    0.27
    -item
    0.27
    建设åĴĮ
    0.27
    material
    0.27
    {_
    0.27
    Activations Density 0.009%

    No Known Activations