© 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. 25-TRANSCODER-HP
    7. 108468
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zej
    -0.28
    elah
    -0.24
    (Cs
    -0.23
    âİĿ
    -0.23
    аÑĤÑĥÑĢ
    -0.23
    ÑĩÑĮ
    -0.23
    ża
    -0.23
     accordingly
    -0.22
    ÑĪе
    -0.22
    обÑĢаÐ
    -0.22
    POSITIVE LOGITS
    ä¸ŃåĽ½çļĦ
    0.86
    ä¸ŃåĽ½
    0.77
    ç¾İåĽ½
    0.76
    æĪijåĽ½
    0.74
     USA
    0.69
    ä¸ŃåĽ½å¤§éĻĨ
    0.66
     China
    0.65
     Germany
    0.63
    åľ¨ä¸ŃåĽ½
    0.61
    ä¸Ńåľĭ
    0.61
    Activations Density 2.355%

    No Known Activations