© 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. 23-TRANSCODER-HP
    7. 24823
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intention
    -0.27
    éªĬ
    -0.26
    cher
    -0.25
    ellation
    -0.24
     miss
    -0.24
    å±ı
    -0.24
    extr
    -0.24
    aff
    -0.24
    ipation
    -0.24
     partition
    -0.24
    POSITIVE LOGITS
    ä¿ĿåĪ©
    0.27
    鹤
    0.27
    çĻ»åħ¥
    0.26
    plotlib
    0.25
    åIJ¬åIJ¬
    0.25
    ãĤ¨ãĥªãĤ¢
    0.24
    å¸ĤæĶ¿åįı
    0.24
     ::↵
    0.24
    èĴ¯
    0.24
    ly
    0.24
    Activations Density 0.161%

    No Known Activations