© 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. 27-TRANSCODER-HP
    7. 7670
    Prev
    Next
    INDEX
    Explanations

    code and searches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     against
    -0.82
     across
    -0.81
     around
    -0.69
    against
    -0.68
     beyond
    -0.63
     within
    -0.63
     Against
    -0.61
     inside
    -0.60
     Across
    -0.58
     away
    -0.57
    POSITIVE LOGITS
     Manuel
    0.26
    portlet
    0.24
    ëĬIJëĥIJ
    0.24
    çļĦä¹łæĥ¯
    0.23
    è¿·
    0.23
    æĪIJç«ĭäºİ
    0.23
    çļĦçľ¼åħī
    0.23
    åĬĽè¿ĺæĺ¯
    0.23
    äºĶåħŃ
    0.23
    Overlap
    0.23
    Activations Density 0.001%

    No Known Activations