© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98400
    Prev
    Next
    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    身å¤Ħ
    -0.26
    ijľ
    -0.25
    æ¸Ń
    -0.25
    çļĦéĢļçŁ¥
    -0.24
    åģļé¥Ń
    -0.23
     nomin
    -0.23
     meille
    -0.23
    èģ©
    -0.23
    æİ¥åı£
    -0.23
     Nep
    -0.23
    POSITIVE LOGITS
     discussed
    0.49
    æľ¬æĸĩ
    0.45
     article
    0.41
    æĸĩç«ł
    0.41
    æĸĩä¸Ń
    0.41
    è¿Ļç¯ĩæĸĩç«ł
    0.39
     mentioned
    0.36
    article
    0.36
     discussion
    0.35
    çļĦæĸĩç«ł
    0.34
    Activations Density 0.003%

    No Known Activations