© 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. 35-TRANSCODER-HP
    7. 38732
    Prev
    Next
    INDEX
    Explanations

    equ

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     equally
    -0.82
     similarly
    -0.60
    åIJĮæł·
    -0.54
     likewise
    -0.53
     equ
    -0.52
     Likewise
    -0.50
     Similarly
    -0.47
    ä¸Ģæł·
    -0.46
     alike
    -0.45
     Equ
    -0.43
    POSITIVE LOGITS
    UTH
    0.27
    lying
    0.26
    Prem
    0.26
     dads
    0.26
    hus
    0.25
     IDs
    0.25
    hom
    0.25
    -id
    0.25
    ums
    0.25
    Ids
    0.24
    Activations Density 0.028%

    No Known Activations