© 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. 53086
    Prev
    Next
    INDEX
    Explanations

    Alcohol and drinks

    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
     sper
    -0.29
     sát
    -0.28
    .sum
    -0.28
     sint
    -0.27
    ä½İ温
    -0.27
     spirit
    -0.27
    ature
    -0.25
    鼶
    -0.24
    çĹ¹
    -0.24
    low
    -0.24
    POSITIVE LOGITS
    é»ijçĻ½
    0.26
    çļĦæĶ¯æĮģ
    0.24
    .Side
    0.24
    /ac
    0.23
    <select
    0.23
    NAL
    0.23
    enso
    0.23
    ileo
    0.23
    ä¸įæĸŃæıIJé«ĺ
    0.23
     wag
    0.23
    Activations Density 0.025%

    No Known Activations