© 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. 162082
    Prev
    Next
    INDEX
    Explanations

    it

    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
    anny
    -0.26
    å¼±
    -0.25
    -be
    -0.23
    execution
    -0.23
    .Document
    -0.23
    家
    -0.23
    ,cp
    -0.23
    å¾IJ
    -0.23
     détail
    -0.23
    +xml
    -0.23
    POSITIVE LOGITS
     anyway
    1.27
     nonetheless
    1.25
     nevertheless
    1.23
     anyways
    1.06
    è¿ĺæĺ¯è¦ģ
    0.96
    è¿ĺæĺ¯ä¼ļ
    0.94
     Nevertheless
    0.93
     still
    0.91
     anyhow
    0.91
    è¿ĺæĺ¯
    0.90
    Activations Density 0.007%

    No Known Activations