© 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. 131161
    Prev
    Next
    INDEX
    Explanations

    Utah

    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
    vant
    -0.26
    代çIJĨ
    -0.25
     LIMITED
    -0.25
    æĻļé¤IJ
    -0.25
    åĶ¯ä¸Ģ
    -0.24
    rô
    -0.23
    Monthly
    -0.23
    lâ
    -0.22
     deter
    -0.22
     dise
    -0.22
    POSITIVE LOGITS
    ivas
    0.26
    ochond
    0.26
    mozilla
    0.26
     positives
    0.25
    leep
    0.25
    istan
    0.25
    èĦį
    0.24
     ras
    0.24
    é¼ĵ
    0.24
    illions
    0.24
    Activations Density 0.019%

    No Known Activations