© 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. 14-TRANSCODER-HP
    7. 39630
    Prev
    Next
    INDEX
    Explanations

    July and August

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     кли
    -0.26
    èįļ
    -0.25
    äºļæ´²
    -0.25
    è¿ĩ度
    -0.25
    wä
    -0.24
    endencies
    -0.24
    oogle
    -0.24
    licated
    -0.24
    æľªç»ı
    -0.24
    æĬķèµĦåŁºéĩij
    -0.24
    POSITIVE LOGITS
    cz
    0.27
    åłĤ
    0.25
     parish
    0.24
    涪
    0.24
    åıįä¹ĭ
    0.24
    .rar
    0.24
     versus
    0.23
     sweep
    0.23
    .embed
    0.23
    .partial
    0.23
    Activations Density 2.687%

    No Known Activations