© 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. 40114
    Prev
    Next
    INDEX
    Explanations

    Legal/business contexts

    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
     moderation
    -0.29
    asion
    -0.28
     subTitle
    -0.26
    åıįä¹ĭ
    -0.26
     moderated
    -0.25
    ownership
    -0.25
    æĹ¥åĩĮæĻ¨
    -0.25
    äºĨä¸Ģåı£
    -0.24
     mane
    -0.24
    oble
    -0.24
    POSITIVE LOGITS
    æĻ¯
    0.27
    gs
    0.27
    èĥĦ
    0.26
     ÄijÃŃch
    0.26
     conced
    0.26
    namespace
    0.26
     out
    0.25
    äººæł¼
    0.25
    _df
    0.24
    èIJ½åľ°
    0.24
    Activations Density 0.843%

    No Known Activations