© 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. 22-TRANSCODER-HP
    7. 113149
    Prev
    Next
    INDEX
    Explanations

    Questions and starting clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æŶ
    -0.30
    itto
    -0.29
    å¾Ĺ好
    -0.28
    æĻĤ
    -0.27
    haft
    -0.25
    æľ¬èĥ½
    -0.24
    _Success
    -0.24
    åĩłçĤ¹
    -0.24
    ç½¢äºĨ
    -0.24
    dart
    -0.23
    POSITIVE LOGITS
    OLUM
    0.25
    çĶ±æĸ¼
    0.24
    assen
    0.24
     pop
    0.24
    uses
    0.23
    INY
    0.23
    iller
    0.23
     Tra
    0.23
    =R
    0.23
    ibile
    0.22
    Activations Density 0.011%

    No Known Activations