© 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. 32-TRANSCODER-HP
    7. 40926
    Prev
    Next
    INDEX
    Explanations

    Matheson

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     apart
    -0.27
     inform
    -0.27
    voy
    -0.25
     Clone
    -0.25
     clone
    -0.25
    à¸ķรา
    -0.25
    fork
    -0.25
     Apart
    -0.24
     trib
    -0.24
     fork
    -0.24
    POSITIVE LOGITS
    GN
    0.26
     Deposit
    0.26
    aru
    0.26
    athlete
    0.25
     pes
    0.25
    æ°ı
    0.25
    æ©Ħ
    0.25
    posium
    0.25
     Tess
    0.25
    èĿĪ
    0.24
    Activations Density 0.001%

    No Known Activations