© 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. 131055
    Prev
    Next
    INDEX
    Explanations

    blog posts and articles

    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
    æŀī
    -0.29
    认è¯ģ
    -0.26
    uru
    -0.25
    ìĤ¬ë¬´
    -0.25
    iert
    -0.24
     yourselves
    -0.24
    -che
    -0.24
    .TypeOf
    -0.24
     ¥
    -0.24
     анализ
    -0.24
    POSITIVE LOGITS
     perceptions
    0.41
     viewers
    0.39
     awareness
    0.35
     acceptance
    0.34
     audiences
    0.34
     perception
    0.33
    åıĹä¼Ĺ
    0.33
    åħ¬ä¼Ĺ
    0.32
    æİ¥åıĹ
    0.32
    纳ç¨İ人
    0.32
    Activations Density 0.002%

    No Known Activations