© 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. 194
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    ç½ij讯
    -0.31
    ordion
    -0.30
    due
    -0.28
     diss
    -0.26
    estatus
    -0.25
    BarItem
    -0.25
    ç´«èī²
    -0.25
    èµĦæºIJåħ±äº«
    -0.25
     own
    -0.25
     expans
    -0.25
    POSITIVE LOGITS
     Mast
    0.27
    iros
    0.27
    åĢ¼
    0.27
     VALUES
    0.26
    Ặ
    0.26
    inals
    0.25
     Shops
    0.24
     swore
    0.24
    .sl
    0.24
    æİĪ
    0.24
    Activations Density 0.086%

    No Known Activations