© 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. 30-TRANSCODER-HP
    7. 95542
    Prev
    Next
    INDEX
    Explanations

    houses and families

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    顼
    -0.30
    åģ¥
    -0.27
    ениÑİ
    -0.27
    fä
    -0.27
    骨干
    -0.26
    æł¼å¼ı
    -0.24
    ritis
    -0.24
    庸
    -0.24
    že
    -0.24
    agon
    -0.24
    POSITIVE LOGITS
     houses
    0.32
     household
    0.32
     family
    0.30
    家åºŃ
    0.28
     households
    0.28
    åİĿ
    0.27
     bags
    0.27
    nor
    0.27
     Houses
    0.27
    lah
    0.26
    Activations Density 0.887%

    No Known Activations