© 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. 23-TRANSCODER-HP
    7. 25423
    Prev
    Next
    INDEX
    Explanations

    code, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    以åıĬ
    -0.88
    以åıĬåħ¶ä»ĸ
    -0.87
     sowie
    -0.79
     serta
    -0.68
     plus
    -0.53
     samt
    -0.52
     oraz
    -0.51
    åıĬåħ¶ä»ĸ
    -0.49
     ainsi
    -0.48
    æĪĸèĢħåħ¶ä»ĸ
    -0.47
    POSITIVE LOGITS
     And
    0.35
    And
    0.35
    ä¸Ķ
    0.35
    并äºİ
    0.34
    并
    0.33
    ï¼Į并
    0.30
    并å°Ĩ
    0.30
     and
    0.29
    å¹¶åľ¨
    0.29
    çĴł
    0.29
    Activations Density 0.001%

    No Known Activations