© 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. 131143
    Prev
    Next
    INDEX
    Explanations

    a, an

    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
    ç¦ıå¾·
    -0.28
    ÑĢид
    -0.26
    etal
    -0.26
    åľ°éģĵ
    -0.25
    _lazy
    -0.25
    ovable
    -0.25
     mee
    -0.25
    è´±
    -0.25
     Bedford
    -0.25
    pard
    -0.24
    POSITIVE LOGITS
    inspection
    0.28
    æ°¸
    0.27
    quality
    0.26
    ANCEL
    0.26
     sens
    0.26
     quot
    0.25
    -quality
    0.25
    ike
    0.25
    inesis
    0.24
     projections
    0.24
    Activations Density 15.607%

    No Known Activations