© 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. 63469
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     xen
    -0.27
    æĪŁ
    -0.26
    osp
    -0.25
     organic
    -0.24
     jets
    -0.24
    myp
    -0.23
    羣
    -0.22
     Organic
    -0.22
     working
    -0.22
    pers
    -0.22
    POSITIVE LOGITS
    بÙĪÙĨ
    0.30
    åĪĨéĴŁåIJİ
    0.27
    ứng
    0.25
    èįª
    0.24
    .unwrap
    0.24
    cef
    0.23
    ningen
    0.23
    ä¸¤åľ°
    0.23
    acin
    0.23
    åŁºç¡Ģä¸Ĭ
    0.23
    Activations Density 26.234%

    No Known Activations

    This feature has no known activations.