© 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. 19-TRANSCODER-HP
    7. 6290
    Prev
    Next
    INDEX
    Explanations

    scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     since
    -0.42
    åĽłä¸º
    -0.39
    since
    -0.39
     because
    -0.38
    because
    -0.35
    åĽłåħ¶
    -0.34
    çĶ±äºİ
    -0.34
    åĽłä¸ºä»ĸ
    -0.32
     поÑģколÑĮкÑĥ
    -0.32
    åĽłçĤº
    -0.30
    POSITIVE LOGITS
    le
    0.31
    èı²
    0.26
    åĩºåľº
    0.26
     Redistribution
    0.25
    retch
    0.25
    èµ¢å¾ĹäºĨ
    0.25
    woke
    0.24
     ranges
    0.24
     ActionController
    0.24
     participates
    0.24
    Activations Density 0.007%

    No Known Activations