© 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. 39548
    Prev
    Next
    INDEX
    Explanations

    Abbreviations, initialisms, and codes

    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
    ov
    -0.28
    ä¼´éļıçĿĢ
    -0.26
    åĩ³
    -0.25
    ов
    -0.25
    TA
    -0.25
     $$
    -0.24
    anos
    -0.24
    ÃŃn
    -0.24
    -android
    -0.24
    zent
    -0.23
    POSITIVE LOGITS
    çļĦ人çī©
    0.31
    arily
    0.28
    agit
    0.28
    oric
    0.28
    æĹ©çĤ¹
    0.27
    çİij
    0.27
     gloss
    0.26
    ä¸ľè¥¿
    0.26
    ç»ĻåĪ«äºº
    0.26
    åıĬ以ä¸Ĭ
    0.26
    Activations Density 0.521%

    No Known Activations