© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9777
    Prev
    Next
    INDEX
    Explanations

    becoming known or popular

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pose
    -0.28
    æĶ¶
    -0.26
    ÑıÑģÑĮ
    -0.26
     DXGI
    -0.25
     Latest
    -0.25
     Offering
    -0.25
    /GPL
    -0.24
    åıĸå¾Ĺ
    -0.24
    ettle
    -0.24
    èĢIJ
    -0.23
    POSITIVE LOGITS
     popularity
    0.33
     solid
    0.32
     renown
    0.29
    æĸ°çļĦä¸Ģå¹´
    0.26
     famous
    0.25
     powerful
    0.25
    ä¸įå¦Ĥ
    0.25
    å·©åĽº
    0.25
     popular
    0.25
     ná»ķi
    0.25
    Activations Density 0.006%

    No Known Activations