© 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. 161854
    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
     anal
    -0.27
    å¿ĥ仪
    -0.26
    /fw
    -0.26
    æĮĩ
    -0.26
    EOS
    -0.25
    ÑĥÑĢÑģ
    -0.25
    _Pin
    -0.25
    è°¬
    -0.24
    orious
    -0.24
    anine
    -0.24
    POSITIVE LOGITS
    institution
    0.29
    terminal
    0.25
    éĢµ
    0.24
    (inst
    0.24
     prospects
    0.24
     crossorigin
    0.24
    ecc
    0.24
    Official
    0.24
     algorithm
    0.24
     getP
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.