© 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. 25-TRANSCODER-HP
    7. 106923
    Prev
    Next
    INDEX
    Explanations

    Nick

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     challenging
    -0.28
    å¾Ĥ
    -0.28
     Tradable
    -0.25
    伸åĩº
    -0.24
    commend
    -0.24
     rendez
    -0.24
     comm
    -0.24
    æĸ°å½¢åĬ¿
    -0.24
    çīĪ
    -0.24
     VOID
    -0.24
    POSITIVE LOGITS
    athe
    0.30
     persönlich
    0.26
     correctly
    0.26
    ols
    0.25
    owo
    0.25
    enton
    0.25
    olic
    0.24
    æľºæ¢°åĮĸ
    0.24
    åŁİ管
    0.24
    personal
    0.24
    Activations Density 0.041%

    No Known Activations