© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56312
    Prev
    Next
    INDEX
    Explanations

    patents and scientific descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    acf
    -0.29
    anas
    -0.28
    arkan
    -0.28
     Chains
    -0.26
     Circ
    -0.26
    kre
    -0.25
     variants
    -0.25
    缴åĪ°
    -0.24
    datatable
    -0.24
     circles
    -0.24
    POSITIVE LOGITS
    iveness
    0.27
    奸
    0.25
    èĦIJ
    0.25
    ossal
    0.25
    èĤ©èĨĢ
    0.24
    èİ«åIJį
    0.24
    ä¸ĩ个
    0.24
    è¿Ļ家ä¼Ļ
    0.23
    entic
    0.23
    yard
    0.23
    Activations Density 0.013%

    No Known Activations