© 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. 24886
    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
     auto
    -0.28
     ro
    -0.25
     one
    -0.25
    ä¸Ģåı£
    -0.24
    çĪ±ä½ł
    -0.23
     me
    -0.23
    rape
    -0.23
     âĢ
    -0.23
     meeting
    -0.23
    Sep
    -0.23
    POSITIVE LOGITS
     Bout
    0.28
    æĭĤ
    0.27
    è¿IJæ²³
    0.25
    æijĺç¼ĸ
    0.25
    istr
    0.24
    sons
    0.24
    çݯçIJĥ
    0.24
    udad
    0.24
    ||(
    0.24
    éĺ´è°ĭ
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.