© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23020
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rotein
    -0.25
    éĻĨ
    -0.25
    éĻ¸
    -0.24
     ÐľÐ¾
    -0.24
    å¼ĤæĢ§
    -0.23
    èįŁ
    -0.23
    ander
    -0.23
    anded
    -0.23
     vet
    -0.23
    :r
    -0.23
    POSITIVE LOGITS
     поб
    0.27
    blend
    0.24
    unread
    0.23
     comforts
    0.23
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥįãĥĥãĥĪ
    0.23
    unda
    0.23
    å¥ijæľº
    0.23
     дел
    0.23
     drives
    0.23
     internet
    0.23
    Activations Density 0.005%

    No Known Activations