© 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. 142138
    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
    æ»Ĥ
    -0.32
     (("
    -0.28
     "'");↵
    -0.26
     season
    -0.26
    忽çĦ¶
    -0.26
    åŃ£èĬĤ
    -0.25
    adir
    -0.25
     pij
    -0.25
    ä¸ĢåĪĨéĴŁ
    -0.25
     continuity
    -0.24
    POSITIVE LOGITS
     Fior
    0.28
    uestas
    0.25
     rods
    0.25
    OOT
    0.25
    uesta
    0.24
     saints
    0.24
    .simps
    0.23
    ç§Ń
    0.23
    izzling
    0.23
     بÙĪاسطة
    0.23
    Activations Density 77.863%

    No Known Activations

    This feature has no known activations.