© 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. 42221
    Prev
    Next
    INDEX
    Explanations

    cancer and smoking

    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
    æĭīåĬ¨
    -0.30
    åķľ
    -0.28
     nons
    -0.27
    éĿŀ
    -0.27
    Smoke
    -0.27
     smoke
    -0.26
    nero
    -0.26
     towns
    -0.26
    icer
    -0.26
    ONS
    -0.26
    POSITIVE LOGITS
    å±Ĥåĩº
    0.29
    鬣
    0.29
    Gu
    0.26
     Hundred
    0.26
    æį¢æĿ¥
    0.26
    eva
    0.26
    æµĨ
    0.25
    shan
    0.25
    çݯå¢ĥ
    0.24
    gu
    0.24
    Activations Density 0.005%

    No Known Activations