© 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. 19-TRANSCODER-HP
    7. 9670
    Prev
    Next
    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mage
    -0.26
    åģıè¿ľ
    -0.25
     (%)
    -0.25
    åįĥéĩĮ
    -0.24
    emm
    -0.24
    å¿IJ
    -0.24
    æľªå¿ħ
    -0.24
    äºĨä¸Ģ份
    -0.24
    龸éģĵ
    -0.23
    主ä¹īèĢħ
    -0.23
    POSITIVE LOGITS
     pers
    0.29
    angelo
    0.28
     persistence
    0.26
    idges
    0.26
     Pers
    0.26
    è®Ń
    0.26
    вед
    0.25
    press
    0.25
    ardo
    0.25
     interaction
    0.24
    Activations Density 0.648%

    No Known Activations