© 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. 32-TRANSCODER-HP
    7. 42423
    Prev
    Next
    INDEX
    Explanations

    your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     That
    -0.36
    That
    -0.34
    that
    -0.32
     rằng
    -0.30
    	that
    -0.29
     that
    -0.29
     bahwa
    -0.29
     THAT
    -0.28
     thats
    -0.28
    å¼ĢäºĨ
    -0.28
    POSITIVE LOGITS
     your
    0.54
     most
    0.45
    most
    0.45
     them
    0.40
    your
    0.40
    ä½łçļĦ
    0.39
    æĤ¨çļĦ
    0.39
     yours
    0.39
     YOUR
    0.38
     MOST
    0.36
    Activations Density 0.000%

    No Known Activations