© 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. 63751
    Prev
    Next
    INDEX
    Explanations

    Amazon

    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
    éĻĮ
    -0.30
    åį´æ²¡æľī
    -0.27
    çģµéŃĤ
    -0.26
     surplus
    -0.26
    åį´æĺ¯
    -0.26
     Tu
    -0.25
    æĺİæĺ¾çļĦ
    -0.25
    åĽŀ头
    -0.24
    sit
    -0.24
    Tu
    -0.24
    POSITIVE LOGITS
    产ä¸ļåĮĸ
    0.26
    ç¡®
    0.26
    çļĦä¸ĢåĪĩ
    0.26
    -match
    0.25
    qualities
    0.24
    -video
    0.24
    çĽ¡
    0.24
     DISCLAIMER
    0.24
    ecc
    0.23
    hv
    0.23
    Activations Density 20.352%

    No Known Activations