© 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. 162012
    Prev
    Next
    INDEX
    Explanations

    meaning

    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
    -minus
    -0.30
    alarm
    -0.28
    Tan
    -0.26
    attering
    -0.26
    æªĶ
    -0.26
    颡
    -0.26
     gyr
    -0.25
    -margin
    -0.24
    orption
    -0.23
     Continent
    -0.23
    POSITIVE LOGITS
     “
    0.42
     "
    0.39
    ï¼ļ“
    0.32
     :"
    0.31
    “They
    0.30
     “âĢ¦
    0.30
    “
    0.29
     Either
    0.28
    “And
    0.27
     "#
    0.27
    Activations Density 0.007%

    No Known Activations