© 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. 31-TRANSCODER-HP
    7. 19712
    Prev
    Next
    INDEX
    Explanations

    harmful/toxic substances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    onder
    -0.30
    ehr
    -0.28
    ceive
    -0.28
     entail
    -0.28
     obr
    -0.28
    provide
    -0.27
     enhance
    -0.27
     quad
    -0.27
    imat
    -0.26
     entails
    -0.26
    POSITIVE LOGITS
    积
    0.31
    污
    0.31
     Accum
    0.31
    Cum
    0.30
     accumulated
    0.29
     accumulating
    0.29
    oris
    0.29
    污æŁĵ
    0.29
     accum
    0.29
    å¯Į
    0.29
    Activations Density 1.111%

    No Known Activations