© 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. 39642
    Prev
    Next
    INDEX
    Explanations

    technology

    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
    åĨħå¤ĸ
    -0.27
    åľ¨è¿Ļ个
    -0.27
    곤
    -0.26
    Compose
    -0.25
    upo
    -0.24
    æĢĿèĢĥ
    -0.24
    enson
    -0.23
    åľ¨è¿ĻéĩĮ
    -0.23
     sensory
    -0.23
    _heat
    -0.23
    POSITIVE LOGITS
    ter
    0.31
    arme
    0.29
    olest
    0.28
     piv
    0.27
    able
    0.26
     Pey
    0.26
    Ī
    0.26
    客æĪ·æľįåĬ¡
    0.26
    pires
    0.26
    被æī§è¡Į
    0.26
    Activations Density 0.080%

    No Known Activations