© 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. 40957
    Prev
    Next
    INDEX
    Explanations

    Escherichia coli

    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
     Antar
    -0.32
    æī£
    -0.29
    wc
    -0.28
    oka
    -0.27
    éĥĬ
    -0.26
    owa
    -0.26
    ront
    -0.26
    achu
    -0.25
    à¤ł
    -0.25
    dbuf
    -0.25
    POSITIVE LOGITS
    çĸı
    0.30
    games
    0.29
    elize
    0.28
    ner
    0.26
    åĴİ
    0.26
     Boeh
    0.26
    Ros
    0.26
    æľ¬æľŁ
    0.25
     E
    0.24
     stem
    0.24
    Activations Density 0.021%

    No Known Activations