© 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. 24242
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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
    west
    -0.28
     tả
    -0.28
    示
    -0.27
    urse
    -0.26
    姿åĬ¿
    -0.26
    æķ´é½IJ
    -0.25
    å¬ī
    -0.24
    æīĵçł´
    -0.24
    fully
    -0.24
    å¿į
    -0.24
    POSITIVE LOGITS
    æĿ²
    0.28
    ä¸įæ¸ħ
    0.27
    elor
    0.27
    pper
    0.26
     cÄĥn
    0.26
    å¤ļä½Ļ
    0.26
    髦
    0.25
    漫éķ¿
    0.24
     AC
    0.24
    embre
    0.24
    Activations Density 0.011%

    No Known Activations