© 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. 161726
    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
    éķĬ
    -0.26
    ãĥĥãĥĪ
    -0.25
     tug
    -0.24
    >Status
    -0.23
     QText
    -0.23
    åŀ£
    -0.23
    thouse
    -0.23
    _reason
    -0.22
     ipt
    -0.22
    cratch
    -0.22
    POSITIVE LOGITS
    æłĩçļĦ
    0.27
    éĿ¢åĮħ
    0.26
     Dest
    0.25
    åĢĴ
    0.25
    ä¿Ħ
    0.25
    uzzi
    0.24
     Gaul
    0.24
    çijķçĸµ
    0.24
    纶
    0.24
    Vict
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.