© 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. 151339
    Prev
    Next
    INDEX
    Explanations

    vocabulary/lexical

    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
    æĿĤå¿Ĺ社
    -0.29
    æĶ¿
    -0.28
    ODY
    -0.25
     ден
    -0.25
    ŀæĢ§
    -0.24
    ifikasi
    -0.24
    connexion
    -0.23
    ifik
    -0.23
    çŀŃ
    -0.23
    æŁĦ
    -0.23
    POSITIVE LOGITS
    æ·ĺ
    0.26
     subs
    0.26
    é£İåı£
    0.25
     tested
    0.25
     recalls
    0.25
    pile
    0.25
    vais
    0.25
    	tests
    0.24
    æł·åŃIJ
    0.24
    Subview
    0.24
    Activations Density 0.434%

    No Known Activations