© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    Automated, technical processes

    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
     daily
    -0.36
    daily
    -0.36
    æ¯ı天
    -0.33
     interactions
    -0.31
    æ¯ıæĹ¥
    -0.30
    äº¤æĽ¿
    -0.29
    çĻ½å¤©
    -0.28
    Daily
    -0.28
     regular
    -0.27
     Daily
    -0.27
    POSITIVE LOGITS
    ç¥ī
    0.30
     narciss
    0.28
     spectrum
    0.27
    建åħļ
    0.26
     spectra
    0.26
     wiring
    0.26
    鼶éĥ¨ä»¶
    0.26
    /port
    0.25
    ä¸įæħİ
    0.24
     Spectrum
    0.24
    Activations Density 0.013%

    No Known Activations