© 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. 162779
    Prev
    Next
    INDEX
    Explanations

    print

    np_max-act · gemini-2.0-flash
    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
    anan
    -0.25
    åĸĥ
    -0.24
    解æŀIJ
    -0.24
    gu
    -0.24
     niá»ĩm
    -0.24
     UCS
    -0.24
    çļĦæĦ¿æľĽ
    -0.24
     Recognition
    -0.24
    cern
    -0.23
    ÑĦин
    -0.23
    POSITIVE LOGITS
     publication
    0.30
     edition
    0.28
    ç¼´
    0.27
    çīĪ
    0.27
    ayı
    0.26
    æ®Ĭ
    0.25
    -ins
    0.25
    rolls
    0.25
     editions
    0.25
    ariat
    0.25
    Activations Density 0.023%

    No Known Activations