© 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. 88968
    Prev
    Next
    INDEX
    Explanations

    creative

    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
     colors
    -0.26
     degrees
    -0.26
    ç®±
    -0.25
    æľŁ
    -0.25
    -color
    -0.24
    æľŁåĨħ
    -0.24
     COLORS
    -0.24
    åħ¬åĬ¡
    -0.24
     skirts
    -0.24
    ffective
    -0.24
    POSITIVE LOGITS
    ught
    0.25
    çĭĹçĭĹ
    0.25
    Ã¼ÃŁ
    0.25
    NZ
    0.24
    zee
    0.24
    ughty
    0.23
    åIJĪçIJĨ
    0.23
    '^
    0.23
    uen
    0.23
     Murdoch
    0.23
    Activations Density 0.041%

    No Known Activations