© 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. 27-TRANSCODER-HP
    7. 8362
    Prev
    Next
    INDEX
    Explanations

    travel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç«Ļåľ¨
    -0.32
    ç«Ļ
    -0.31
    ç«ĻçĤ¹
    -0.31
    åģľçķĻ
    -0.30
     Park
    -0.29
    åģľä¸ĭ
    -0.29
    drop
    -0.29
     drop
    -0.29
     station
    -0.28
     park
    -0.28
    POSITIVE LOGITS
     travel
    0.60
    æĹħè¡Į
    0.60
     traveled
    0.58
    è¿IJè¾ĵ
    0.57
     traveling
    0.56
     travels
    0.56
     transported
    0.56
     transportation
    0.54
     transport
    0.52
     travelled
    0.51
    Activations Density 0.002%

    No Known Activations