© 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. 27-TRANSCODER-HP
    7. 8972
    Prev
    Next
    INDEX
    Explanations

    Farming industry and activities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĸĹäºī
    -0.29
    æĶ»åĿļ
    -0.29
    çļĦç»ıéªĮ
    -0.28
    iasm
    -0.27
    åħ¬çĦ¶
    -0.26
    áºį
    -0.26
    .rmi
    -0.25
    大åİħ
    -0.24
     Baghd
    -0.24
    +xml
    -0.24
    POSITIVE LOGITS
    çݳ
    0.36
     regions
    0.29
     operations
    0.27
     business
    0.27
     region
    0.26
     instruct
    0.26
    eg
    0.25
    duc
    0.25
    ariat
    0.25
    补水
    0.25
    Activations Density 0.004%

    No Known Activations