© 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. 30-TRANSCODER-HP
    7. 96917
    Prev
    Next
    INDEX
    Explanations

    hot and cold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æµħ
    -0.28
    cratch
    -0.28
     Siri
    -0.28
    ckett
    -0.27
    ersh
    -0.27
    åħ¥èĤ¡
    -0.27
    anas
    -0.26
    ani
    -0.26
     Slo
    -0.24
    æĸľ
    -0.24
    POSITIVE LOGITS
     provision
    0.34
    oge
    0.28
     remot
    0.27
    åIJİæľŁ
    0.26
    ps
    0.25
    Expose
    0.24
    åĽłç´ł
    0.24
    æľŁ
    0.24
    çī¹æĢ§
    0.24
     Télé
    0.23
    Activations Density 0.001%

    No Known Activations