© 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. 12-TRANSCODER-HP
    7. 22091
    Prev
    Next
    INDEX
    Explanations

    code or legal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è§Į
    -0.35
    uur
    -0.29
    uo
    -0.26
    uhan
    -0.26
    çħħ
    -0.26
    owa
    -0.26
     links
    -0.26
     linking
    -0.24
    æĪ·
    -0.24
    ign
    -0.24
    POSITIVE LOGITS
    åı¯ä»¥æĬĬ
    0.29
    便åĪ©
    0.28
     Tech
    0.28
    miss
    0.27
    涯
    0.26
    çŃĸ
    0.25
     Diff
    0.25
    .Diff
    0.25
    åĪĨæѧ
    0.25
    èģĮä¸ļ
    0.25
    Activations Density 0.001%

    No Known Activations