© 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. 19-TRANSCODER-HP
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    have, been, comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    паÑĤ
    -0.27
     Prec
    -0.27
    manship
    -0.26
    [group
    -0.25
    强迫
    -0.25
    æīĵæī«
    -0.25
    isches
    -0.24
    æݨéĢģ
    -0.24
     chr
    -0.24
    Dump
    -0.23
    POSITIVE LOGITS
    æĺ¯ä¸įä¼ļ
    0.26
    ocht
    0.26
     Rentals
    0.26
    éĥ½ä¸įä¼ļ
    0.26
    .inf
    0.25
    æĸĩåĮĸåĴĮ
    0.25
     unto
    0.25
    нÑİ
    0.25
    _legal
    0.25
    亿åħĥ以ä¸Ĭ
    0.24
    Activations Density 0.053%

    No Known Activations