© 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. 24-TRANSCODER-HP
    7. 151439
    Prev
    Next
    INDEX
    Explanations

    technical troubleshooting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     everyone
    -0.28
     Everyone
    -0.27
     blaze
    -0.25
    æ³³
    -0.25
     everybody
    -0.25
    ãĥ£
    -0.25
    achable
    -0.25
    Everyone
    -0.24
    ä¸įæĸŃå¢ŀ强
    -0.24
    åıĮèħ¿
    -0.23
    POSITIVE LOGITS
    ypad
    0.25
     copyright
    0.25
    ató
    0.24
    ebile
    0.24
    ycin
    0.24
    bufio
    0.24
    orthand
    0.24
    aternion
    0.24
    favor
    0.24
    åIJ¬å¾Ĺ
    0.24
    Activations Density 0.799%

    No Known Activations