© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    accordance

    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
    åIJįå½ķ
    -0.28
     StringTokenizer
    -0.26
    folios
    -0.24
    éĺ¿æĭī伯
    -0.23
     conco
    -0.23
    æĹ¥æĬ¥ç¤¾
    -0.22
    ebra
    -0.22
    åħīçݯ
    -0.22
     beds
    -0.22
     myster
    -0.21
    POSITIVE LOGITS
    sole
    0.35
     governed
    0.25
    åıĭ好
    0.25
    oto
    0.24
    ponsor
    0.24
    lag
    0.24
    æīĢ
    0.24
    éģĵ
    0.23
    æľ¬åħ¬åı¸
    0.23
    ity
    0.23
    Activations Density 1.503%

    No Known Activations