© 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. 30-TRANSCODER-HP
    7. 94881
    Prev
    Next
    INDEX
    Explanations

    geographic data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    豪éŨ
    -0.27
    æĢ
    -0.27
    æİ¥å¾ħ
    -0.27
    flix
    -0.26
    ç»Ĭ
    -0.24
    pled
    -0.24
    çĽijäºĭä¼ļ
    -0.24
    åĴĢ
    -0.24
    ancell
    -0.24
    åĬª
    -0.24
    POSITIVE LOGITS
    åľ°çIJĨ
    0.81
     ge
    0.81
     geographic
    0.74
     cart
    0.72
     Ge
    0.71
     survey
    0.71
    Ge
    0.70
     Geographic
    0.67
    ge
    0.65
    geo
    0.65
    Activations Density 1.111%

    No Known Activations