© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130645
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯Ń
    -0.29
     sem
    -0.28
    ç»ıéªĮ
    -0.27
    åīįåIJİ
    -0.27
     that
    -0.26
    è¨Ģ
    -0.26
     sam
    -0.25
    类似çļĦ
    -0.25
    sb
    -0.25
    ä¹ĭéĹ´
    -0.25
    POSITIVE LOGITS
    åħļç»ĦæĪIJåijĺ
    0.30
    DAQ
    0.28
    深交
    0.27
    å°ıç¼ĸ
    0.27
    åħļç»Ħ书记
    0.26
    yne
    0.26
    ocus
    0.26
    anchors
    0.26
    acas
    0.25
    anan
    0.25
    Activations Density 19.319%

    No Known Activations