© 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. 22-TRANSCODER-HP
    7. 113020
    Prev
    Next
    INDEX
    Explanations

    Snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    举
    -0.35
    ç£ķ
    -0.27
    çĥŃ
    -0.25
    ãĥIJãĥ³
    -0.25
    ille
    -0.25
     Worlds
    -0.25
     young
    -0.25
    ow
    -0.25
    çĶµæ±ł
    -0.25
    Disposition
    -0.25
    POSITIVE LOGITS
    å°Ĩèĩªå·±çļĦ
    0.27
    =YES
    0.27
    expect
    0.26
     '%'
    0.26
    åį´åıijçİ°
    0.26
    MER
    0.25
    åıĪ好
    0.25
    ä¸į代表
    0.24
     expecting
    0.24
    好åIJĹ
    0.24
    Activations Density 0.009%

    No Known Activations