© 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. 41753
    Prev
    Next
    INDEX
    Explanations

    eno

    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
    士
    -0.29
    æĸ¹
    -0.28
    å¹¹
    -0.26
    rów
    -0.25
    夹
    -0.24
    åľº
    -0.24
    çĶ«
    -0.24
     settling
    -0.24
     Millenn
    -0.24
    èĽĨ
    -0.23
    POSITIVE LOGITS
    éĢĨè¡Į
    0.30
     tung
    0.27
    mong
    0.26
     outright
    0.26
    åıįæŃ£
    0.24
    .song
    0.24
    agan
    0.23
    æĪĸå¤ļ
    0.23
    çļĦ女人
    0.23
    éĩĮçļĦ
    0.23
    Activations Density 0.073%

    No Known Activations