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. 53891
    Prev
    Next
    INDEX
    Explanations

    Communist leaders

    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
     accommodation
    -0.32
    羣åģĩ
    -0.31
    TestId
    -0.26
    èį£
    -0.25
    çħ
    -0.25
    线ä¸Ĭ线ä¸ĭ
    -0.25
    çİij
    -0.25
    æ°´éĿ¢
    -0.25
    phot
    -0.24
     televised
    -0.24
    POSITIVE LOGITS
    示
    0.29
    å¼
    0.28
    è¿ĺ好
    0.26
    zas
    0.26
    .datas
    0.25
    .writeString
    0.25
    æķ¢äºİ
    0.25
     fined
    0.25
    hop
    0.24
    dux
    0.24
    Activations Density 0.002%

    No Known Activations