© 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. 9205
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    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
    æĪĸå¤ļ
    -0.32
    ekyll
    -0.29
     futuro
    -0.27
    either
    -0.26
    责任ç¼ĸè¾ij
    -0.25
    è¦ģä¹Ī
    -0.25
     subTitle
    -0.24
    ocus
    -0.24
    pton
    -0.24
     iceberg
    -0.24
    POSITIVE LOGITS
     Ferm
    0.27
     half
    0.26
     certainly
    0.26
     response
    0.26
     fit
    0.25
     fits
    0.25
     stip
    0.24
    ROS
    0.24
    ros
    0.24
    ONSE
    0.24
    Activations Density 0.011%

    No Known Activations