© 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. 20-TRANSCODER-HP
    7. 131000
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    esty
    -0.26
    opsy
    -0.25
    使åij½
    -0.25
     overdue
    -0.24
    (coder
    -0.24
    resh
    -0.23
    egral
    -0.23
    :{}
    -0.23
    èįĨ
    -0.23
     Airways
    -0.23
    POSITIVE LOGITS
    èijŃ
    0.26
     |--
    0.25
    èī¯å¥½çļĦ
    0.25
    quo
    0.24
    #----------------------------------------------------------------------------
    0.24
    eya
    0.23
    еÑģÑĤво
    0.23
    upt
    0.23
     fact
    0.22
     quot
    0.22
    Activations Density 23.754%

    No Known Activations