© 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. 107032
    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
    oku
    -0.27
    adt
    -0.26
    çĿ£
    -0.25
    ึà¸ģ
    -0.24
    -suite
    -0.24
     ilk
    -0.24
     exceeded
    -0.24
    CAN
    -0.24
    rière
    -0.24
    à¸Ķำ
    -0.24
    POSITIVE LOGITS
    çļĦ羣å®ŀ
    0.26
    associ
    0.25
    peror
    0.25
    æĮŁ
    0.25
    åľ¨çݩ家
    0.24
    çĹ¹
    0.24
    ĥģ
    0.24
    ENCY
    0.23
     fı
    0.23
    çļĦæķ´ä½ĵ
    0.23
    Activations Density 46.669%

    No Known Activations

    This feature has no known activations.