© 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. 12-TRANSCODER-HP
    7. 22351
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åij¨åĪĬ
    -0.28
    .ms
    -0.27
    京津åĨĢ
    -0.27
     Mosul
    -0.27
    .microsoft
    -0.27
    å¾IJå·ŀ
    -0.27
     diaper
    -0.26
     spel
    -0.26
    æ²Ĥ
    -0.26
     Affero
    -0.26
    POSITIVE LOGITS
     Australian
    0.54
    Australian
    0.52
     Australians
    0.51
    æĤīå°¼
    0.50
    Australia
    0.50
     Australia
    0.47
     Aussie
    0.47
    澳洲
    0.46
     NSW
    0.45
     Canberra
    0.45
    Activations Density 0.024%

    No Known Activations