© 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. 44103
    Prev
    Next
    INDEX
    Explanations

    Investing and finance

    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
     capital
    -0.30
    åijĨ
    -0.28
     fasc
    -0.27
     Tau
    -0.27
    æī«ä¸Ģæī«
    -0.26
    capital
    -0.26
    å¤ĩ
    -0.25
    립
    -0.25
     Stereo
    -0.25
    æ»ļåĬ¨
    -0.25
    POSITIVE LOGITS
     short
    0.35
     dumped
    0.33
    çŁŃ
    0.30
     Wash
    0.29
    /value
    0.29
     shorts
    0.28
     SHORT
    0.27
    åĥ¹åĢ¼
    0.27
    æ²ĥ
    0.27
     day
    0.27
    Activations Density 0.008%

    No Known Activations