© 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. 20-TRANSCODER-HP
    7. 142025
    Prev
    Next
    INDEX
    Explanations

    Text extracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cular
    -0.28
    term
    -0.27
    ç¡®
    -0.27
    izedName
    -0.26
    adj
    -0.26
    é¦Ļ
    -0.25
    ä¸Ńåįİæ°ijæĹı
    -0.25
    æĬĹåĩ»
    -0.25
    å¼Ĥ
    -0.25
    (strlen
    -0.25
    POSITIVE LOGITS
     Baker
    0.29
    å·²ç»ı被
    0.28
    å·²ç»ıåľ¨
    0.27
    æĹ¥äº§
    0.27
    塾
    0.26
    å·²ç»ıæĺ¯
    0.26
    佩æĪ´
    0.26
    egis
    0.24
    iamond
    0.24
    -leading
    0.24
    Activations Density 8.443%

    No Known Activations