© 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. 24-TRANSCODER-HP
    7. 149169
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    di
    -0.28
    éĶ¡
    -0.25
    elect
    -0.25
     loc
    -0.25
     convers
    -0.24
    æĤ´
    -0.24
     health
    -0.24
    oufl
    -0.24
    ibrate
    -0.24
    dio
    -0.23
    POSITIVE LOGITS
    aira
    0.28
    ioni
    0.27
     èĭ¥è¦ģ
    0.26
    å¼ĢåºĹ
    0.26
     viewDidLoad
    0.25
    æĬķèµĦé¢Ŀ
    0.25
    Crime
    0.25
    åİ¿æĶ¿åºľ
    0.24
    IDO
    0.24
    ymous
    0.24
    Activations Density 0.175%

    No Known Activations