© 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. 108029
    Prev
    Next
    INDEX
    Explanations

    Foreign/similar words

    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
    æĽ´å¤ļçļĦæĺ¯
    -0.31
     primarily
    -0.28
     principalmente
    -0.27
    åĨįåİ»
    -0.27
    åĨį说
    -0.27
     disjoint
    -0.26
    æĽ´ä¸º
    -0.25
    äºĨåĩł
    -0.25
    riv
    -0.25
    å¥łåŁº
    -0.25
    POSITIVE LOGITS
     similar
    0.31
    åIJĮæł·
    0.30
    åIJĮæł·çļĦ
    0.29
    类似çļĦ
    0.28
    æľīè¿Ļæł·çļĦ
    0.27
    ä¸Ģæł·çļĦ
    0.27
    ä¹Łæĺ¯å¦ĤæѤ
    0.27
     desta
    0.27
    è¿Ļä¹Ł
    0.27
     assets
    0.26
    Activations Density 0.933%

    No Known Activations