© 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. 24400
    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
    administrator
    -0.28
    æ°´åŁŁ
    -0.26
    .iso
    -0.26
     Cut
    -0.25
    thro
    -0.25
    ï¼ļ
    -0.25
    æł¼å±Ģ
    -0.24
    .bmp
    -0.24
    frau
    -0.24
    å°±æѤ
    -0.23
    POSITIVE LOGITS
    带ä¸Ĭ
    0.27
    éħįä¸Ĭ
    0.27
    ä¸Ģæĸ¹
    0.26
    åĽŀé¦ĸ
    0.26
     native
    0.25
    .native
    0.25
     Recap
    0.25
    ĺ认
    0.24
    Pes
    0.24
     mockery
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.