© 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. 30-TRANSCODER-HP
    7. 96197
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    áo
    -0.27
    ç§ijåѦ
    -0.27
    mó
    -0.26
    ê·¼
    -0.25
     surround
    -0.25
     пÑĥ
    -0.24
    horn
    -0.24
    é£İ鼨
    -0.24
    hots
    -0.24
    bag
    -0.24
    POSITIVE LOGITS
    rega
    0.35
    cribe
    0.29
    axios
    0.28
    eldon
    0.26
    èį¯
    0.26
    éķĽ
    0.25
    ä¸Ĭä¼ł
    0.25
    ideo
    0.25
    cean
    0.24
    羿
    0.24
    Activations Density 0.882%

    No Known Activations