© 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. 39412
    Prev
    Next
    INDEX
    Explanations

    .com and .net

    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
     rek
    -0.29
    Drink
    -0.29
    hop
    -0.27
    hei
    -0.27
    ê³łìļĶ
    -0.26
    eps
    -0.25
    æŀŀ
    -0.25
    iegel
    -0.24
    htag
    -0.24
    ยว
    -0.24
    POSITIVE LOGITS
    ost
    0.26
    æľ¬ç½ijç«Ļ
    0.26
    idon
    0.25
    Mitch
    0.24
    è¿Ļ座åŁİå¸Ĥ
    0.24
    isan
    0.24
     Uncomment
    0.23
     Pars
    0.23
    ä¸Ģä¸ĭ
    0.23
    åŃĻæĤŁç©º
    0.23
    Activations Density 0.210%

    No Known Activations