© 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. 64024
    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
    shield
    -0.27
    UnderTest
    -0.27
    fav
    -0.27
    æ¡Ĩ
    -0.26
    #$
    -0.26
    quake
    -0.25
    éĦ¢
    -0.25
    æķĪåºĶ
    -0.25
    åºļ
    -0.24
    oce
    -0.24
    POSITIVE LOGITS
    5
    0.28
    ced
    0.25
     prag
    0.24
     å®ŀ
    0.24
    3
    0.24
     fifty
    0.24
    è¯ķæİ¢
    0.24
     conver
    0.23
    acci
    0.23
     navig
    0.23
    Activations Density 2.822%

    No Known Activations

    This feature has no known activations.