© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7844
    Prev
    Next
    INDEX
    Explanations

    Various document snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     calls
    -0.29
    issance
    -0.25
     Great
    -0.25
     third
    -0.24
    еле
    -0.24
    对åħ¶è¿Ľè¡Į
    -0.24
    çĬį
    -0.24
    ãģĦãģ¾ãģĽãĤĵ
    -0.24
    upported
    -0.23
     swings
    -0.23
    POSITIVE LOGITS
    sar
    0.29
    s
    0.26
    srv
    0.26
    俱ä¹IJéĥ¨
    0.26
    serv
    0.26
    ematic
    0.26
    servers
    0.26
    -generation
    0.25
    å«Ĥ
    0.25
    sync
    0.25
    Activations Density 1.168%

    No Known Activations