© 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. 14-TRANSCODER-HP
    7. 41053
    Prev
    Next
    INDEX
    Explanations

    leadership, charismatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egers
    -0.26
    é¦Ļ
    -0.26
    åĩ¡æĺ¯
    -0.25
    åľ¨å¹¿å·ŀ
    -0.25
     incremental
    -0.24
    getPost
    -0.24
    ä»»ä½ķå½¢å¼ı
    -0.24
    ä¸Ģ页
    -0.24
    enga
    -0.24
    马åħĭæĢĿ
    -0.24
    POSITIVE LOGITS
    ampa
    0.28
    isoft
    0.24
    .Business
    0.24
    å¾Ĵ
    0.24
    yme
    0.24
    .SE
    0.23
    çĤ³
    0.23
    æĭŃ
    0.23
    EA
    0.23
    pong
    0.23
    Activations Density 0.112%

    No Known Activations