© 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. 56573
    Prev
    Next
    INDEX
    Explanations

    Names and descriptions of people

    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
    éķĽ
    -0.28
    ujet
    -0.27
    审计
    -0.26
    å®ŀæĸ½ç»ĨåĪĻ
    -0.25
    ä¸Ńæłĩ
    -0.24
    èİ·å¾ĹäºĨ
    -0.24
    :void
    -0.24
    æı½
    -0.24
     giấc
    -0.24
    iae
    -0.23
    POSITIVE LOGITS
    rance
    0.28
     sectors
    0.27
     roadside
    0.25
    广éĺĶ
    0.25
    ulence
    0.25
    å¿ĥåĬ¨
    0.25
    NESS
    0.25
    compound
    0.25
    iveness
    0.24
    iness
    0.24
    Activations Density 0.000%

    No Known Activations