© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 350
    Prev
    Next
    INDEX
    Explanations

    window

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inflate
    -0.27
     Zub
    -0.25
    rift
    -0.25
     pi
    -0.24
     mastering
    -0.24
    åı¯æĥ³
    -0.24
    .relative
    -0.24
     Relative
    -0.24
    å¾ĹäºĨ
    -0.23
    诣
    -0.23
    POSITIVE LOGITS
    çªĹåı£
    0.42
    çªĹ
    0.38
     window
    0.35
     windows
    0.34
    çªĹæĪ·
    0.30
    çªĹå¤ĸ
    0.30
    (window
    0.29
    windows
    0.28
    window
    0.28
     Window
    0.27
    Activations Density 0.195%

    No Known Activations