© 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. 41537
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text snippets

    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
    宵
    -0.30
    AGER
    -0.27
    iran
    -0.27
    ?>>
    -0.27
    inking
    -0.27
    çļĦæĦıè§ģ
    -0.26
    shall
    -0.26
    emos
    -0.26
    clude
    -0.26
    (es
    -0.26
    POSITIVE LOGITS
    åĽ°
    0.31
    驱åĬ¨
    0.30
    è¶ĭåIJij
    0.28
     switched
    0.26
     drives
    0.26
    ENA
    0.25
     consciousness
    0.25
    RN
    0.25
    驶
    0.25
    owoÅĽci
    0.24
    Activations Density 0.314%

    No Known Activations