© 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. 23-TRANSCODER-HP
    7. 162688
    Prev
    Next
    INDEX
    Explanations

    Instructions and usage examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aptcha
    -0.26
    æľīä¸įåIJĮçļĦ
    -0.26
    è¿ĩåİ»çļĦ
    -0.25
     redhead
    -0.25
    å¤ļç§įå½¢å¼ı
    -0.25
    ä¹ĺ车
    -0.24
    æľīèī²
    -0.24
     anthology
    -0.24
    éļIJç§ģ
    -0.24
    岫
    -0.24
    POSITIVE LOGITS
     Barb
    0.30
    æľĪä¸ĭ
    0.26
     SPE
    0.26
    éĵ¾
    0.26
     Revenue
    0.25
    een
    0.25
    å½ĵä»ĸ
    0.25
     when
    0.25
     kto
    0.24
     known
    0.24
    Activations Density 0.002%

    No Known Activations