© 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. 141723
    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¶İ
    -0.29
    rex
    -0.26
    éĹ³
    -0.26
     Stockholm
    -0.25
    onn
    -0.25
    \Input
    -0.25
     lobby
    -0.24
    ä¹į
    -0.24
     rollout
    -0.24
     Completely
    -0.24
    POSITIVE LOGITS
    iane
    0.25
     ({↵
    0.25
     ATA
    0.24
    èĿ´èĿ¶
    0.24
     AFC
    0.24
    паÑĤ
    0.23
    åĪĨä¼ļ
    0.23
    .degree
    0.23
    ({↵↵
    0.23
     fortn
    0.23
    Activations Density 42.705%

    No Known Activations

    This feature has no known activations.