© 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. 19321
    Prev
    Next
    INDEX
    Explanations

    Malaria and related medication

    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
     leopard
    -0.29
    onor
    -0.28
    RS
    -0.28
    è¯ļæĦı
    -0.27
    estruct
    -0.26
    ster
    -0.25
    enstein
    -0.25
     Mich
    -0.24
    ãģĦãģ¾ãģĽãĤĵ
    -0.24
    igers
    -0.24
    POSITIVE LOGITS
     mix
    0.27
    etest
    0.26
    å¥İ
    0.26
    -placeholder
    0.26
    éŃģ
    0.26
    elines
    0.26
    	sm
    0.26
    hq
    0.25
    æ¾į
    0.25
    äºĮæīĭ
    0.25
    Activations Density 0.918%

    No Known Activations