© 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. 44065
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical formulations

    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
    åĬŁ
    -0.28
    亲å¯Ĩ
    -0.26
    argo
    -0.26
    çļ±çº¹
    -0.26
     Phelps
    -0.25
    èģļä¼ļ
    -0.25
    .Wrap
    -0.24
    enda
    -0.24
    -leading
    -0.24
    ầu
    -0.24
    POSITIVE LOGITS
    erk
    0.28
    åħ¥
    0.28
     control
    0.27
    æݧåĪ¶
    0.26
    秧
    0.26
     Carb
    0.26
    yw
    0.26
    åı£
    0.25
    ays
    0.25
     controlled
    0.25
    Activations Density 0.053%

    No Known Activations