© 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. 4793
    Prev
    Next
    INDEX
    Explanations

    asterisk

    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
    --[
    -0.27
     completely
    -0.25
     propagated
    -0.24
    ä¸įä¸ĭ
    -0.24
     DISCLAIMED
    -0.24
     '':↵
    -0.24
    ioms
    -0.23
    _MISS
    -0.23
    éĨĴäºĨ
    -0.23
    æľĪæľ«
    -0.23
    POSITIVE LOGITS
    cs
    0.30
    ÑĤÑĥÑĢ
    0.26
     Bas
    0.26
    /high
    0.24
    brace
    0.24
    alem
    0.24
    ...",↵
    0.24
    åľ°æĸ¹
    0.24
    èĤłéģĵ
    0.23
    unding
    0.23
    Activations Density 0.858%

    No Known Activations