© 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. 110
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms

    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
    宿
    -0.29
    ä¸ĵæłı
    -0.28
    inem
    -0.25
     ×ŀק
    -0.25
     VIA
    -0.24
    KEN
    -0.24
    æŃ£åľ¨è¿Ľè¡Į
    -0.24
    _syntax
    -0.24
    Father
    -0.24
    uish
    -0.24
    POSITIVE LOGITS
    adt
    0.25
    æŃ£çīĪ
    0.25
    okie
    0.25
    raud
    0.25
    ilen
    0.25
    ISTS
    0.24
    repair
    0.24
    è¦ģçľĭ
    0.24
    æĿ¥ä¸´
    0.24
    /;↵
    0.24
    Activations Density 0.386%

    No Known Activations