© 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. 9402
    Prev
    Next
    INDEX
    Explanations

    such

    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
    åıªæĥ³
    -0.27
     selectively
    -0.25
    æĽ¿ä»£
    -0.24
    ä¸Ģåı£
    -0.24
    eldon
    -0.24
    /em
    -0.24
    vider
    -0.24
    éĺ¶æ¢¯
    -0.24
    spaces
    -0.23
    elta
    -0.23
    POSITIVE LOGITS
     perish
    0.34
     prolong
    0.31
    æįŁèĢĹ
    0.30
    éķ¿æŶéĹ´
    0.29
     aging
    0.29
     lifespan
    0.29
     fres
    0.28
    æľ½
    0.28
     ageing
    0.28
     durability
    0.27
    Activations Density 0.082%

    No Known Activations