© 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. 40949
    Prev
    Next
    INDEX
    Explanations

    assault and legal battles

    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
    ç½²
    -0.32
    åįĪé¤IJ
    -0.28
     strict
    -0.26
    严
    -0.26
    æ²¥
    -0.25
     fick
    -0.24
    èĸĦ
    -0.24
     gint
    -0.24
     Pe
    -0.24
    Pe
    -0.24
    POSITIVE LOGITS
     eup
    0.27
    åĭī
    0.27
    .imp
    0.25
    á»ĩt
    0.25
    ãĥĭãĥ¥
    0.25
    моÑĢ
    0.25
    çĬ¯
    0.25
    è¿Ŀ
    0.24
    outs
    0.24
     Territory
    0.24
    Activations Density 0.002%

    No Known Activations