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. 11-TRANSCODER-HP
    4. 54444
    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_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Ordinal
    -0.27
    cup
    -0.27
     Pond
    -0.27
    åıĪæĺ¯
    -0.26
    åħ¼å®¹
    -0.26
    ipa
    -0.25
    ardin
    -0.25
     subscribe
    -0.25
    letal
    -0.24
    ders
    -0.24
    POSITIVE LOGITS
    é«ĺå±±
    0.28
    :<?
    0.25
    åѦä¼ļ
    0.25
     spe
    0.25
     Solomon
    0.24
    æł·
    0.24
    :inline
    0.23
    èIJ½
    0.23
     Callback
    0.23
    ç«Ļ
    0.23
    Activations Density 0.010%

    No Known Activations