© 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. 42529
    Prev
    Next
    INDEX
    Explanations

    code/instructions

    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
     liá»ĩu
    -0.28
    headed
    -0.27
    ophil
    -0.24
     Pyramid
    -0.24
     headings
    -0.24
     titled
    -0.24
    çľ¼åīįçļĦ
    -0.24
    -headed
    -0.24
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.24
     superficial
    -0.24
    POSITIVE LOGITS
     cycle
    0.28
     change
    0.28
    ик
    0.28
    	change
    0.26
    change
    0.26
    åĭŀ
    0.26
    .Dom
    0.25
    _cycle
    0.25
    åĨĪ
    0.25
    edo
    0.25
    Activations Density 0.000%

    No Known Activations