© 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. 32-TRANSCODER-HP
    7. 43196
    Prev
    Next
    INDEX
    Explanations

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bero
    -0.29
    айн
    -0.28
    proto
    -0.27
    ol
    -0.26
     cig
    -0.26
    INCLUDE
    -0.26
    交åıī
    -0.26
    coverage
    -0.26
     cyl
    -0.25
    Dry
    -0.24
    POSITIVE LOGITS
    worked
    0.39
     worked
    0.37
    å·¥ä½ľ
    0.36
     working
    0.35
    WORK
    0.34
     work
    0.34
    work
    0.34
    ä¸ªå·¥ä½ľ
    0.32
     Working
    0.32
    working
    0.32
    Activations Density 0.009%

    No Known Activations