© 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. 6211
    Prev
    Next
    INDEX
    Explanations

    was

    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
    ä¸įæĪIJ
    -0.29
    aal
    -0.28
    æĮij
    -0.26
    æĤ¬
    -0.25
    èł
    -0.25
     invent
    -0.25
    åı¯è¾¾
    -0.25
    ä¸ī大
    -0.24
     invention
    -0.24
    uai
    -0.24
    POSITIVE LOGITS
    pii
    0.28
    oler
    0.28
    .constructor
    0.28
    åł¡
    0.27
    ny
    0.26
     >(
    0.26
    ieee
    0.25
    stry
    0.25
    istringstream
    0.25
    ÃŃg
    0.24
    Activations Density 0.030%

    No Known Activations