© 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. 21937
    Prev
    Next
    INDEX
    Explanations

    beautiful

    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
    oner
    -0.28
    ÐĶÐķ
    -0.27
    éļħ
    -0.27
     Kern
    -0.26
    æķıæĦŁ
    -0.25
    æĴ¤ç¦»
    -0.25
    oning
    -0.25
    åĽ½éģĵ
    -0.24
    åľ¨æĪijçļĦ
    -0.23
    ixel
    -0.23
    POSITIVE LOGITS
    Ñĩе
    0.27
    èķ¨
    0.26
    antes
    0.26
    Annotations
    0.25
    Folders
    0.25
    寿
    0.24
    elves
    0.24
     Futures
    0.24
    antic
    0.24
    æŀ¶
    0.24
    Activations Density 0.005%

    No Known Activations