Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 826
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sert
    -0.31
    æĪijä»¬åľ¨
    -0.27
    nga
    -0.27
    ewise
    -0.27
    atus
    -0.26
     broken
    -0.26
    ç¥Ŀç¦ı
    -0.26
    åľ¨ä¸Ģ个
    -0.25
    è¿ŀ线
    -0.24
    esture
    -0.24
    POSITIVE LOGITS
    ä¸įèµ·
    0.29
     Vanity
    0.25
    å쬦
    0.25
    .Utility
    0.24
     Journal
    0.24
    ç´ļ
    0.23
    ãĤ¸ãĥ¼
    0.23
     âĦĸ
    0.23
    è¿Ļæīį
    0.23
     Odin
    0.23
    Activations Density 0.004%

    No Known Activations