© 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. 140567
    Prev
    Next
    INDEX
    Explanations

    appear

    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
    coes
    -0.27
    è°İ
    -0.26
    สà¸ĩà¸ļ
    -0.25
    pei
    -0.24
     vá»ijn
    -0.24
    uzu
    -0.24
    ToStr
    -0.24
     famously
    -0.24
    .bd
    -0.23
    æ£Ģç´¢
    -0.23
    POSITIVE LOGITS
    æ»ĭ
    0.28
    èĭŀ
    0.27
    uae
    0.27
    å§ij
    0.26
     few
    0.26
    åĪĿæŃ¥
    0.25
    éĿ¢å¯¹
    0.24
    -ing
    0.24
    åĬ©
    0.24
    reon
    0.24
    Activations Density 13.128%

    No Known Activations