© 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. 33-TRANSCODER-HP
    7. 52728
    Prev
    Next
    INDEX
    Explanations

    Michael

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     amet
    -0.32
    ara
    -0.31
    halt
    -0.27
    åĸ»
    -0.25
    Refer
    -0.25
    顺åºĶ
    -0.25
    atum
    -0.25
    -angular
    -0.24
    idental
    -0.24
    æĬķ
    -0.24
    POSITIVE LOGITS
    Æ°ng
    0.28
    mdi
    0.28
    ysis
    0.28
    iki
    0.26
     stacking
    0.26
     Conv
    0.25
    ç´ĭ
    0.24
     kn
    0.24
    ysts
    0.23
    åģ»
    0.23
    Activations Density 0.010%

    No Known Activations