© 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. 6027
    Prev
    Next
    INDEX
    Explanations

    U.S. patent numbers

    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
    ä¸įå¼Ģ
    -0.27
    arti
    -0.25
    eria
    -0.25
    erus
    -0.25
    åĦ¿
    -0.24
    endir
    -0.23
     PRES
    -0.23
    бил
    -0.23
    ser
    -0.23
     zip
    -0.22
    POSITIVE LOGITS
    fty
    0.28
    visions
    0.27
     Flesh
    0.25
    åѦèĢħ
    0.25
    ftype
    0.25
    maxlength
    0.24
    éĻIJ
    0.24
    reur
    0.23
    rego
    0.23
     scraping
    0.23
    Activations Density 0.069%

    No Known Activations