© 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. 23559
    Prev
    Next
    INDEX
    Explanations

    Emails, code, web content

    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
    æĪijä»¬åľ¨
    -0.32
    æĸŁ
    -0.28
    dire
    -0.28
    äºĨä¸Ģ份
    -0.27
    enario
    -0.26
     ourselves
    -0.26
     revival
    -0.26
    å½ĵæĪij们
    -0.25
     Inform
    -0.24
     sommes
    -0.24
    POSITIVE LOGITS
    jis
    0.29
     sonic
    0.26
    yes
    0.25
    æµł
    0.25
    wi
    0.25
    ör
    0.25
    ya
    0.24
    arti
    0.24
     caul
    0.24
     ayr
    0.23
    Activations Density 0.030%

    No Known Activations