© 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. 41541
    Prev
    Next
    INDEX
    Explanations

    say "the"

    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
    è¿Ļæĸ¹éĿ¢
    -0.34
    åľ¨æĪij
    -0.33
    çļĦéĤ£ä¸Ģ
    -0.25
    ä¸ŃæľĢ
    -0.25
    箦
    -0.25
    çļĦä¸įåIJĮ
    -0.24
    èĩªæĿ¥
    -0.24
    çļĦä¸Ģ
    -0.24
    çļĦçĭ¬çī¹
    -0.24
    æīĢéľĢè¦ģ
    -0.23
    POSITIVE LOGITS
     the
    0.87
    the
    0.71
    The
    0.54
    	the
    0.51
    ,the
    0.51
    _the
    0.50
    .the
    0.49
     The
    0.49
     teh
    0.41
     THE
    0.40
    Activations Density 0.003%

    No Known Activations