© 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. 9-TRANSCODER-HP
    7. 29119
    Prev
    Next
    INDEX
    Explanations

    Canterbury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     yourself
    -0.33
     myself
    -0.33
     sit
    -0.28
    ryn
    -0.27
     himself
    -0.27
    åĪį
    -0.27
    __(*
    -0.27
    ä¸įæŃ»
    -0.26
    侧éĿ¢
    -0.26
    åİķ
    -0.26
    POSITIVE LOGITS
     comparator
    0.27
    lük
    0.24
     remot
    0.24
    å¨ģèĥģ
    0.24
     behavioural
    0.24
    nad
    0.24
    ncoder
    0.23
    nesia
    0.23
    #ad
    0.23
     PRESS
    0.23
    Activations Density 0.171%

    No Known Activations