© 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. 31-TRANSCODER-HP
    7. 17855
    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_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æµĭè¯ķ
    -0.43
     test
    -0.34
    gtest
    -0.34
     Tests
    -0.33
    ãĥĨãĤ¹ãĥĪ
    -0.33
    ptest
    -0.32
    _TESTS
    -0.32
    CTest
    -0.32
    à¸Ĺà¸Ķสà¸Ńà¸ļ
    -0.32
     Test
    -0.31
    POSITIVE LOGITS
     which
    0.57
    which
    0.50
    Which
    0.42
    åĵª
    0.41
     their
    0.40
     Which
    0.39
     коÑĤоÑĢое
    0.38
     the
    0.37
    åĵªä¸ª
    0.36
     WHICH
    0.35
    Activations Density 0.207%

    No Known Activations