© 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. 19-TRANSCODER-HP
    7. 4859
    Prev
    Next
    INDEX
    Explanations

    archive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useParams
    -0.29
    ãģĵãģ¨
    -0.27
    åı¥è¯Ŀ
    -0.23
     LoginComponent
    -0.23
    erness
    -0.23
     Boulder
    -0.23
     compliment
    -0.22
    -handed
    -0.22
    æĦīå¿«
    -0.22
    ç¿ħèĨĢ
    -0.22
    POSITIVE LOGITS
    -worthy
    0.27
    yards
    0.26
    stry
    0.25
    /package
    0.25
     abroad
    0.24
     fou
    0.23
    /repository
    0.23
    edly
    0.23
     бÑİ
    0.23
     needless
    0.23
    Activations Density 1.114%

    No Known Activations