© 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. 182
    Prev
    Next
    INDEX
    Explanations

    riet

    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
    æ¹
    -0.27
    ffiti
    -0.25
    æŀľ
    -0.24
    .pk
    -0.24
    apur
    -0.24
    设
    -0.24
    -path
    -0.24
    童年
    -0.23
    è·¯å¾Ħ
    -0.23
    europ
    -0.23
    POSITIVE LOGITS
     expend
    0.28
    bol
    0.27
     polled
    0.26
     erfolgreich
    0.25
    Disclaimer
    0.25
    ç»ıéªĮåĴĮ
    0.25
    bai
    0.24
    æĸ¡
    0.24
     readline
    0.24
     afterwards
    0.24
    Activations Density 0.006%

    No Known Activations