© 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. 152
    Prev
    Next
    INDEX
    Explanations

    suffixes

    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
    ready
    -0.27
     kul
    -0.26
    头
    -0.25
    reate
    -0.24
    ocy
    -0.24
    acle
    -0.23
    REN
    -0.23
     Ã¶ÄŁ
    -0.23
     blockSize
    -0.23
    -packages
    -0.23
    POSITIVE LOGITS
    enums
    0.27
    .dx
    0.26
    æ¦Ħ
    0.25
    äºĮ人
    0.24
    guid
    0.24
    们çļĦ
    0.24
     incon
    0.24
     possibly
    0.24
    导
    0.24
    çıŃéķ¿
    0.23
    Activations Density 0.019%

    No Known Activations