© 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. 31-TRANSCODER-HP
    7. 17759
    Prev
    Next
    INDEX
    Explanations

    Medical/legal disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĤ£ä¹Ī容æĺĵ
    -0.27
    éĢģåĩº
    -0.27
     fig
    -0.26
    FromBody
    -0.25
    åĺ´è§Ĵ
    -0.25
     dreamed
    -0.25
    eing
    -0.24
    adden
    -0.24
    æ´Ĺå¹²åĩĢ
    -0.23
    é³ľ
    -0.23
    POSITIVE LOGITS
     Wax
    0.28
     Addresses
    0.28
    ãĤµãĥ³
    0.27
    Address
    0.26
    æł·åĵģ
    0.26
    循çݯ
    0.25
     attendance
    0.25
     Attendance
    0.24
     Att
    0.24
    åĶ§
    0.24
    Activations Density 0.109%

    No Known Activations