© 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. 95888
    Prev
    Next
    INDEX
    Explanations

    Statistics and percentages

    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
     many
    -0.30
    许å¤ļ
    -0.29
    åħ«åįģ
    -0.28
    å¾Īå¤ļ
    -0.28
     eighty
    -0.28
    WX
    -0.27
    許å¤ļ
    -0.27
    íĥķ
    -0.27
    work
    -0.26
    ä¸įå°ij
    -0.25
    POSITIVE LOGITS
    è£ħå¤ĩ
    0.28
     Speakers
    0.27
    ]+'
    0.27
    æ»ļåĬ¨
    0.27
     Rams
    0.27
    aday
    0.27
    çī©èµĦ
    0.26
     Mel
    0.25
     getProperty
    0.25
    uste
    0.25
    Activations Density 0.886%

    No Known Activations