© 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. 31-TRANSCODER-HP
    7. 19353
    Prev
    Next
    INDEX
    Explanations

    Medical conditions and policing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ľä¸ºä¸Ģ个
    -0.29
    缸åħ³çļĦ
    -0.28
    é³ĥ
    -0.28
    ä»ĸ们
    -0.27
    åºĶåıĬæŶ
    -0.25
    ä¿Ŀ
    -0.25
    åĪļ好
    -0.24
     THEIR
    -0.24
    ä»ĸ们çļĦ
    -0.24
    ierce
    -0.24
    POSITIVE LOGITS
     based
    0.35
     subjects
    0.29
    based
    0.27
    åŁºäºİ
    0.27
     clients
    0.27
     patients
    0.25
     fortunes
    0.25
     property
    0.25
     people
    0.25
     Based
    0.25
    Activations Density 1.949%

    No Known Activations