© 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. 41564
    Prev
    Next
    INDEX
    Explanations

    Iron and/or copper

    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
    èĢĮè¨Ģ
    -0.27
     magnets
    -0.27
    åijĪ
    -0.27
    为ä¾ĭ
    -0.25
     magnet
    -0.25
    æĻºæħ§
    -0.25
    èŀŃ
    -0.24
    赶ä¸Ĭ
    -0.24
     appreciated
    -0.24
    æĿ¥è®²
    -0.23
    POSITIVE LOGITS
    bourg
    0.28
     dbg
    0.27
    venge
    0.25
    çĶ±æѤ
    0.25
    çī¯
    0.24
    erez
    0.24
    ibur
    0.24
    enda
    0.23
     /*!<
    0.23
    pressive
    0.23
    Activations Density 0.237%

    No Known Activations