© 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. 22-TRANSCODER-HP
    7. 88026
    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_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonded
    -0.25
    éŁ³ä¹IJä¼ļ
    -0.25
    NetBar
    -0.24
    imers
    -0.24
     im
    -0.24
    oucher
    -0.23
     vert
    -0.23
    ายà¸Ļ
    -0.23
    .NaN
    -0.23
    kB
    -0.23
    POSITIVE LOGITS
    LEY
    0.30
    panse
    0.26
     Hait
    0.24
    ä»ĸçļĦ
    0.24
    è¸Ŀ
    0.23
    太å¤ļçļĦ
    0.22
    .yml
    0.22
    太å¤ļ
    0.22
     proced
    0.22
    -too
    0.22
    Activations Density 0.004%

    No Known Activations