© 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. 24-TRANSCODER-HP
    7. 150655
    Prev
    Next
    INDEX
    Explanations

    pregnant/pregnancy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kids
    -0.36
     children
    -0.34
     kids
    -0.34
    让åŃ©åŃIJ
    -0.33
    children
    -0.32
     Children
    -0.31
    Kids
    -0.31
    åŃ©åŃIJ
    -0.31
    åŃ©åŃIJ们
    -0.30
    åŃ©åŃIJçļĦ
    -0.28
    POSITIVE LOGITS
    åŃķå¦ĩ
    0.41
    åŃķæľŁ
    0.40
    åŃķ
    0.40
     trimest
    0.40
    å¦Ĭå¨ł
    0.39
    æĢĢåŃķ
    0.39
    产
    0.38
     gravid
    0.37
     pregnant
    0.35
    åŃķèĤ²
    0.32
    Activations Density 1.641%

    No Known Activations