© 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. 25-TRANSCODER-HP
    7. 109524
    Prev
    Next
    INDEX
    Explanations

    beauty and hygiene

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    é¢ģ
    -0.28
    emouth
    -0.27
     Shopping
    -0.26
     Integrated
    -0.26
    iator
    -0.26
    Browse
    -0.25
    -dot
    -0.25
    af
    -0.24
    ãģ½
    -0.24
    поÑĤ
    -0.24
    POSITIVE LOGITS
    .ls
    0.28
    纯
    0.28
    åĵ²åѦ
    0.27
    ·¸
    0.27
     entren
    0.24
    OnError
    0.24
    润æ»ij
    0.24
    'util
    0.24
     '{"
    0.24
    ç´Ķ
    0.24
    Activations Density 0.914%

    No Known Activations