© 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. 40945
    Prev
    Next
    INDEX
    Explanations

    medical studies/criteria

    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
     Discrim
    -0.27
    gence
    -0.26
    votes
    -0.25
    åĬĽè¿ĺæĺ¯
    -0.25
    許
    -0.25
    -le
    -0.25
    ä¸įæľį
    -0.24
     Uncomment
    -0.24
    iesta
    -0.23
    æİĺ
    -0.23
    POSITIVE LOGITS
    aska
    0.29
    æµĨ
    0.27
     clinical
    0.25
    çĪ±ç¾İ
    0.25
    ackle
    0.24
     ple
    0.24
     the
    0.24
    ей
    0.24
    istringstream
    0.24
     attempted
    0.23
    Activations Density 0.002%

    No Known Activations