© 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. 9810
    Prev
    Next
    INDEX
    Explanations

    Code and software licenses

    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
     commerce
    -0.34
     capitalism
    -0.31
     religion
    -0.30
     mathematics
    -0.28
     medicine
    -0.28
     science
    -0.28
    çļĦåŁºç¡Ģ
    -0.28
     inf
    -0.28
     agriculture
    -0.27
     commission
    -0.27
    POSITIVE LOGITS
    ONT
    0.28
    ont
    0.27
    ANNOT
    0.27
     Designs
    0.26
    设计çIJĨ念
    0.25
    Ut
    0.25
     timespec
    0.24
     jobject
    0.24
    åĪ©
    0.24
    vale
    0.24
    Activations Density 0.007%

    No Known Activations