© 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. 24979
    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
     My
    -0.31
     m
    -0.29
     over
    -0.28
     As
    -0.28
     Right
    -0.28
     Up
    -0.27
     Again
    -0.27
     Proceed
    -0.27
     all
    -0.27
     Ex
    -0.27
    POSITIVE LOGITS
    semb
    0.29
    æł¸å¿ĥåĮº
    0.28
    ç½ijå°ıç¼ĸ
    0.27
    senha
    0.26
    abhäng
    0.26
    å¼Ģåıij建设
    0.26
    uars
    0.25
    -provider
    0.25
     merch
    0.25
     disagreement
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.