© 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. 19708
    Prev
    Next
    INDEX
    Explanations

    drilling wells

    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
    åı£æ°´
    -0.29
    æĸ°çĶŁ
    -0.27
     !***
    -0.27
     tun
    -0.26
     adap
    -0.25
    转æį¢
    -0.25
    amus
    -0.25
    opi
    -0.25
    aos
    -0.24
    çļĦåķĨåĵģ
    -0.24
    POSITIVE LOGITS
     cutter
    0.32
    еÑĩно
    0.28
    导åIJij
    0.28
     scre
    0.27
    é¹ħ
    0.27
    éĢł
    0.27
    romo
    0.26
    åİļéĩį
    0.26
    å¥Ĺ
    0.26
    dings
    0.26
    Activations Density 0.181%

    No Known Activations