© 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. 20-TRANSCODER-HP
    7. 130991
    Prev
    Next
    INDEX
    Explanations

    code/math/database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    adult
    -0.29
    æĢİä¹ĪåĬŀ
    -0.28
    æĢİä¹Īçľĭ
    -0.28
    KEN
    -0.27
    å¼Ĥåij³
    -0.27
     tempting
    -0.26
    olah
    -0.26
     den
    -0.25
    æ¯Ķåĸ»
    -0.25
    ä¸įåIJĪ
    -0.25
    POSITIVE LOGITS
    ...]
    0.29
    uto
    0.26
    ]._
    0.26
     }//
    0.25
    -comments
    0.24
    /self
    0.23
    ýt
    0.23
     Declarations
    0.23
    åħ¨åĽ½äººæ°ij
    0.23
    orent
    0.23
    Activations Density 29.465%

    No Known Activations