© 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. 7889
    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
    西路
    -0.28
     taxable
    -0.27
    æĴ¥
    -0.27
    osta
    -0.26
    å¼Ģä¸ļ
    -0.25
    æĬ¥ä»ĩ
    -0.25
    æĭ¨
    -0.25
    Opera
    -0.24
    esse
    -0.24
    æŀ¶
    -0.24
    POSITIVE LOGITS
    éķ¿æķĪæľºåĪ¶
    0.26
    rites
    0.25
    ingle
    0.25
    erto
    0.24
    aru
    0.24
     dice
    0.24
     habit
    0.24
     Bin
    0.23
    æľīåħ³éĥ¨éŨ
    0.23
     Slug
    0.23
    Activations Density 0.076%

    No Known Activations

    This feature has no known activations.