© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161668
    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
    eer
    -0.31
    eba
    -0.28
    erot
    -0.26
    Ø«ÙĪر
    -0.26
    cript
    -0.25
    cert
    -0.25
    script
    -0.25
    gregate
    -0.24
     outnumber
    -0.24
    ery
    -0.24
    POSITIVE LOGITS
    oulos
    0.26
    ç®Ķ
    0.26
    /inet
    0.26
    åĨį次
    0.24
    ç«ĭéĿ¢
    0.24
    lient
    0.24
    å·²ä¹ħçļĦ
    0.24
     Cupertino
    0.23
     stump
    0.23
    åħ¶æ¬¡æĺ¯
    0.23
    Activations Density 0.093%

    No Known Activations

    This feature has no known activations.