© 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. 32-TRANSCODER-HP
    7. 42530
    Prev
    Next
    INDEX
    Explanations

    del

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лаÑģ
    -0.26
    .generated
    -0.26
    æĬ¥èĢĥ
    -0.26
    ductive
    -0.25
    eks
    -0.24
    èµĦ产éĩįç»Ħ
    -0.24
    æĭīæĸ¯
    -0.23
    สะ
    -0.23
    èĸĦå¼±
    -0.23
    _Enc
    -0.23
    POSITIVE LOGITS
     delivery
    0.95
    交
    0.90
     delivered
    0.85
     Delivery
    0.85
     deliver
    0.80
    delivery
    0.79
    交ä»ĺ
    0.78
    Delivery
    0.74
     delivering
    0.72
     deliveries
    0.69
    Activations Density 0.001%

    No Known Activations