© 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. 161860
    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
     Handlers
    -0.29
    ç³ł
    -0.29
    maal
    -0.28
    صÙĪÙĦ
    -0.25
    æ²¹æ°Ķ
    -0.25
    KeyEvent
    -0.25
    amenti
    -0.25
    ASIC
    -0.24
    IVED
    -0.24
    aked
    -0.24
    POSITIVE LOGITS
     Olympia
    0.30
     mb
    0.27
     allo
    0.26
     dequeue
    0.25
    éķ¦
    0.25
    ev
    0.24
     embodied
    0.24
     dup
    0.24
    trap
    0.24
     overrun
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.