© 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. 4-TRANSCODER-HP
    7. 373
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç±ģ
    -0.34
     pallet
    -0.26
     ex
    -0.25
    好åIJĹ
    -0.24
    =back
    -0.24
    å¹ķ
    -0.24
    å¼Ģéĩĩ
    -0.23
     hook
    -0.23
    åģ¥åħ¨
    -0.23
    éķ°
    -0.23
    POSITIVE LOGITS
    çķĶ
    0.28
    tors
    0.27
    ¹Ħ
    0.26
    боÑĢ
    0.26
    tür
    0.25
     Rodrig
    0.25
    enis
    0.24
    qry
    0.24
     DAC
    0.24
    bson
    0.24
    Activations Density 0.372%

    No Known Activations

    This feature has no known activations.