© 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. 211
    Prev
    Next
    INDEX
    Explanations

    ron

    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
    urons
    -0.28
     spre
    -0.27
    inct
    -0.25
    ensively
    -0.25
    whelming
    -0.25
    ivot
    -0.23
    opard
    -0.23
    encion
    -0.23
    asy
    -0.23
    PLY
    -0.23
    POSITIVE LOGITS
    er
    0.26
     Emmy
    0.26
    orph
    0.25
    o
    0.25
     Essential
    0.23
    eve
    0.23
    ä¼ģä¸ļåĴĮ
    0.23
    edb
    0.23
     Agent
    0.23
    :
    0.23
    Activations Density 0.005%

    No Known Activations