© 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. 6489
    Prev
    Next
    INDEX
    Explanations

    Code and 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
    伤
    -0.27
    feeding
    -0.25
    åĨľ
    -0.25
     BASIS
    -0.25
    kees
    -0.24
    VERR
    -0.24
    every
    -0.24
    éĻĭ
    -0.24
     Bright
    -0.23
    ä¿ĿæĮģ
    -0.23
    POSITIVE LOGITS
    ãģķãģĦ
    0.29
    txn
    0.25
     tech
    0.24
    ator
    0.24
     Van
    0.24
    onga
    0.24
    sap
    0.24
     intervening
    0.24
    åĽłåŃIJ
    0.23
     ÅĽc
    0.23
    Activations Density 0.857%

    No Known Activations