© 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. 54574
    Prev
    Next
    INDEX
    Explanations

    tested

    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
     friday
    -0.25
    æĿĢæīĭ
    -0.24
    cest
    -0.24
    options
    -0.24
    BufferSize
    -0.23
    ее
    -0.23
    DOC
    -0.23
    thon
    -0.23
    лем
    -0.23
    avana
    -0.23
    POSITIVE LOGITS
    tested
    0.39
     tested
    0.35
     Tested
    0.34
     Tests
    0.32
     checked
    0.31
     tests
    0.30
    æį·
    0.29
    Tests
    0.29
    -tests
    0.29
     studied
    0.29
    Activations Density 0.035%

    No Known Activations