© 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. 128927
    Prev
    Next
    INDEX
    Explanations

    Uncertainty/optionality

    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
    inated
    -0.28
    ç»Ŀ对ä¸įä¼ļ
    -0.25
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.25
    æķĪ
    -0.25
    çĮĽçĦ¶
    -0.24
     Pru
    -0.24
     releases
    -0.24
    éĽĨèģļ
    -0.24
     reductions
    -0.24
     revelations
    -0.24
    POSITIVE LOGITS
    ets
    0.30
    ä¹±
    0.28
    ares
    0.27
    shore
    0.27
    ture
    0.27
    å¿«ä¸ī
    0.25
     fitting
    0.25
    att
    0.25
    zt
    0.25
    äºĤ
    0.24
    Activations Density 0.006%

    No Known Activations