© 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. 18-TRANSCODER-HP
    7. 88117
    Prev
    Next
    INDEX
    Explanations

    Freud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éķĿ
    -0.26
    æĺ¼å¤ľ
    -0.25
    è¿
    -0.24
    亦
    -0.24
    æįī
    -0.24
    说ä¸įå®ļ
    -0.23
    ¬ģ
    -0.23
    ında
    -0.23
    让æĤ¨
    -0.23
    åľ°äº§
    -0.23
    POSITIVE LOGITS
    -Smith
    0.25
     native
    0.25
    lood
    0.25
    MO
    0.25
    strate
    0.25
    åľ°ä¸ĭæ°´
    0.24
    ç²Ł
    0.24
    æĽ´æĸ°
    0.24
     Update
    0.24
    æĪªèĩ³
    0.24
    Activations Density 5.868%

    No Known Activations