© 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. 24901
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çļĦæĸ¹åIJij
    -0.28
    ä¼ı
    -0.27
    ucci
    -0.27
    /plain
    -0.26
    ddd
    -0.26
    legg
    -0.26
    æĮĩ示
    -0.25
     bushes
    -0.24
    anging
    -0.24
    æĸ¹åIJij
    -0.24
    POSITIVE LOGITS
    å®ŀ践活åĬ¨
    0.29
    #ga
    0.28
    å®ŀè·µä¸Ń
    0.27
    emens
    0.27
     tour
    0.26
    bose
    0.26
     tours
    0.26
    agements
    0.25
    agini
    0.25
    社ä¼ļå®ŀè·µ
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.