© 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. 20-TRANSCODER-HP
    7. 141327
    Prev
    Next
    INDEX
    Explanations

    Technical/academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢİä¹Īçľĭ
    -0.25
    kir
    -0.25
    é³Ŀ
    -0.24
     Become
    -0.24
     HERE
    -0.24
    PROC
    -0.23
    Proc
    -0.23
    質
    -0.23
    æĴ¥
    -0.23
     ë§Į
    -0.23
    POSITIVE LOGITS
    -capital
    0.27
    rollers
    0.26
    èĢĥå¯Ł
    0.26
    åİŁå§ĭ
    0.26
    æ²»
    0.25
    quete
    0.25
     reflects
    0.25
    ises
    0.24
    istine
    0.24
     sector
    0.24
    Activations Density 0.177%

    No Known Activations