© 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. 163064
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     at
    -0.67
     tại
    -0.49
    ItemAt
    -0.46
    	at
    -0.39
    _at
    -0.36
     Tại
    -0.36
    AtIndex
    -0.34
     ợ
    -0.33
    At
    -0.32
    -at
    -0.32
    POSITIVE LOGITS
    æµĩ
    0.29
    è·Łä½ł
    0.27
    åŃ£èĬĤ
    0.25
    ẵ
    0.25
    abus
    0.24
    dater
    0.24
    .nodeName
    0.23
    ï¼Į请
    0.23
    season
    0.23
     african
    0.23
    Activations Density 0.033%

    No Known Activations