© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 86
    Prev
    Next
    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    di
    -0.29
     yü
    -0.28
     diagnostic
    -0.28
     diagn
    -0.26
    ni
    -0.26
    lient
    -0.25
    áĥĵ
    -0.25
     controlling
    -0.25
    ä¸įåĩĨ
    -0.24
    î
    -0.24
    POSITIVE LOGITS
    ç»´å¥ĩ
    0.27
     ksz
    0.27
     Kits
    0.26
     помеÑīениÑı
    0.24
    èĪį
    0.24
     Ster
    0.24
    ÑĢоÑĪ
    0.24
    为ä¼ģä¸ļ
    0.24
    ë¶
    0.24
    .eye
    0.23
    Activations Density 0.541%

    No Known Activations