© 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. 33-TRANSCODER-HP
    7. 52990
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     first
    -0.68
    first
    -0.58
    _first
    -0.51
    First
    -0.51
    (first
    -0.49
    	first
    -0.48
    [first
    -0.48
    çļĦ第ä¸Ģ
    -0.48
    .first
    -0.47
    第ä¸Ģ
    -0.46
    POSITIVE LOGITS
     consulted
    0.35
     dealt
    0.31
     dragged
    0.29
    -years
    0.29
    -formed
    0.28
     approached
    0.28
     entertained
    0.28
    oce
    0.28
     attended
    0.28
     reached
    0.28
    Activations Density 0.054%

    No Known Activations