© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    porter
    -0.27
    夫
    -0.27
    >New
    -0.25
     fres
    -0.25
     cripp
    -0.24
    åĪ¶åº¦æĶ¹éĿ©
    -0.23
    çļĦèīºæľ¯
    -0.23
     Passed
    -0.23
    夷
    -0.23
    _Printf
    -0.23
    POSITIVE LOGITS
    -wise
    0.26
    è¾¹çķĮ
    0.25
     refrain
    0.25
    entes
    0.25
    WISE
    0.24
    ENTE
    0.24
     STEP
    0.24
    veis
    0.24
    (NULL
    0.24
    å¹´èµ·
    0.24
    Activations Density 0.212%

    No Known Activations

    This feature has no known activations.