© 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. 161807
    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
     easiest
    -0.31
    æľĢåħ³éĶ®çļĦ
    -0.28
    èĭķ
    -0.28
    æľĢåŁºæľ¬
    -0.27
     safest
    -0.27
     happiest
    -0.27
     intimacy
    -0.26
     scenes
    -0.26
    uling
    -0.26
    æ¯Ķè¾ĥå¤ļ
    -0.26
    POSITIVE LOGITS
     extended
    0.28
     trib
    0.28
    (permission
    0.27
     longer
    0.26
    ãĤ¤ãĥĪ
    0.25
    å¤ļæł·åĮĸ
    0.25
    osh
    0.25
     coordin
    0.25
     Ill
    0.24
    á»ĭ
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.