© 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. 24-TRANSCODER-HP
    7. 149398
    Prev
    Next
    INDEX
    Explanations

    developing countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç¡ķ
    -0.26
    .Experimental
    -0.25
     paddingTop
    -0.24
     grap
    -0.24
     cant
    -0.24
    (zip
    -0.24
     `\
    -0.23
    ä¸įçķĻ
    -0.23
    fos
    -0.23
    /customer
    -0.23
    POSITIVE LOGITS
     tropical
    0.42
    举åįĹäºļ
    0.42
    éĿŀæ´²
    0.42
     Africa
    0.39
    ä¸ĸçķĮ
    0.38
    åį°åº¦
    0.37
    æŁ¬åŁĶ寨
    0.36
    Africa
    0.36
     impoverished
    0.36
    -Saharan
    0.35
    Activations Density 1.366%

    No Known Activations