© 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. 1
    Prev
    Next
    INDEX
    Explanations

    express

    np_max-act · gemini-2.0-flash

    mentions of the act of expressing or conveying feelings, thoughts, impressions, or remorse

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    èı²å°Ķ
    -0.29
    bib
    -0.28
    clin
    -0.25
    Mathf
    -0.24
    åºĸ
    -0.24
    icl
    -0.24
     hold
    -0.24
    绣çŃ¹æİ¨è¿Ľ
    -0.24
    ä¿ĿæĬ¤åĮº
    -0.24
    reinterpret
    -0.24
    POSITIVE LOGITS
    eneg
    0.26
     '
    0.26
    çĸ½
    0.25
    计åħ¥
    0.25
     Enter
    0.25
    ry
    0.25
    enter
    0.24
    a
    0.24
    Enter
    0.24
    lopen
    0.24
    Activations Density 0.065%

    No Known Activations