© 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. 111456
    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
    oku
    -0.27
    %x
    -0.25
    _",
    -0.24
    resa
    -0.24
    GetX
    -0.24
    ãģ¯ãģļ
    -0.24
    anka
    -0.24
    åģĥ
    -0.23
    odo
    -0.23
    çļĦå°±æĺ¯
    -0.23
    POSITIVE LOGITS
    两家
    0.33
    åĨ³å®ļ
    0.25
    åħ«ä¸ª
    0.24
    út
    0.24
    Behind
    0.24
    ereg
    0.24
    èĵĿ
    0.23
    ä¸ĥ个
    0.23
     blue
    0.23
    åįģäºĮ
    0.23
    Activations Density 0.056%

    No Known Activations