© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53005
    Prev
    Next
    INDEX
    Explanations

    word "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
    Not in Any Lists

    No Comments

    Negative Logits
    aires
    -0.27
    ưỡng
    -0.26
    bian
    -0.26
    thic
    -0.25
     strokeLine
    -0.25
    ulis
    -0.25
    Ĵáŀ
    -0.25
    éĦī
    -0.25
    utor
    -0.25
    zew
    -0.24
    POSITIVE LOGITS
     tests
    0.33
     Tests
    0.30
     testing
    0.30
    åIJį
    0.28
    åIJį声
    0.28
     Testing
    0.28
    Tests
    0.27
    tests
    0.27
    sel
    0.26
    Testing
    0.26
    Activations Density 0.016%

    No Known Activations