© 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. 163103
    Prev
    Next
    INDEX
    Explanations

    crisis

    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
    iac
    -0.31
     alphabetical
    -0.29
    sk
    -0.26
    æĺĨä»ij
    -0.26
    folios
    -0.26
    igator
    -0.26
     /^\
    -0.26
    ewan
    -0.25
    主æĦı
    -0.25
    é¼»
    -0.25
    POSITIVE LOGITS
     crisis
    0.30
     larger
    0.28
    ç´§å¼ł
    0.27
    é£İæļ´
    0.27
    ç°ł
    0.26
     once
    0.26
     shortage
    0.25
    åĭķ
    0.25
     troubles
    0.25
     crises
    0.25
    Activations Density 0.168%

    No Known Activations