© 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. 19-TRANSCODER-HP
    7. 8633
    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
    说å®ŀ
    -0.26
    ä¸Ģç¬Ķ
    -0.26
    说åĪ°
    -0.25
    ãģ«åĩº
    -0.25
    ocket
    -0.24
    ove
    -0.24
    itat
    -0.24
    ç¹ģ
    -0.24
     prof
    -0.24
     trav
    -0.24
    POSITIVE LOGITS
    ãĤ¸ãĥ£ãĥ³
    0.27
    æ¸ħæ´ģèĥ½æºIJ
    0.27
     cân
    0.26
    eur
    0.26
    æľªçŁ¥
    0.24
    conciliation
    0.23
    elastic
    0.23
     bif
    0.23
    è°ģçŁ¥éģĵ
    0.23
    ÙĥÙĦÙģ
    0.23
    Activations Density 0.563%

    No Known Activations

    This feature has no known activations.