© 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. 9844
    Prev
    Next
    INDEX
    Explanations

    math, code, technical writing

    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
     order
    -1.28
    order
    -1.09
     Order
    -1.07
    -order
    -1.02
     orders
    -1.02
    Order
    -0.99
    _order
    -0.94
    订åįķ
    -0.94
    	order
    -0.91
     ORDER
    -0.88
    POSITIVE LOGITS
    yen
    0.27
    ailer
    0.26
    feb
    0.25
     terminator
    0.24
     überh
    0.24
    åıŁ
    0.24
    yi
    0.23
    è¾ĥ强çļĦ
    0.23
     lag
    0.23
    /core
    0.23
    Activations Density 0.003%

    No Known Activations