© 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. 27-TRANSCODER-HP
    7. 56589
    Prev
    Next
    INDEX
    Explanations

    affordable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Renaissance
    -0.27
     Celsius
    -0.26
    åŃº
    -0.26
    ç½ķ
    -0.26
    ediator
    -0.26
     rep
    -0.25
    è¿Ļåĩłå¤©
    -0.24
    iosis
    -0.24
     Basics
    -0.24
    RAW
    -0.23
    POSITIVE LOGITS
    å¼Ģæ°´
    0.28
    anyak
    0.28
     traced
    0.26
    ohon
    0.25
    ufe
    0.25
    elled
    0.25
     anchored
    0.25
    íĤ¹
    0.25
    serter
    0.25
    egration
    0.24
    Activations Density 0.001%

    No Known Activations