© 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. 18-TRANSCODER-HP
    7. 89282
    Prev
    Next
    INDEX
    Explanations

    Random text and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bais
    -0.29
    bes
    -0.27
    éĺ´
    -0.27
     âľĵ
    -0.26
     gap
    -0.25
    ç½¢
    -0.25
     necessities
    -0.24
     previous
    -0.24
    gap
    -0.24
    кÑĢаÑĤ
    -0.24
    POSITIVE LOGITS
    ldb
    0.30
    èĬ±æľµ
    0.30
    lich
    0.26
     newText
    0.25
     CultureInfo
    0.25
     Encoding
    0.25
    转åĮĸ
    0.25
    ipped
    0.25
    æľīä»·åĢ¼çļĦ
    0.25
    ellen
    0.24
    Activations Density 1.004%

    No Known Activations