© 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. 99143
    Prev
    Next
    INDEX
    Explanations

    more, reading

    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
     --↵
    -0.26
    æĽ´å¥½
    -0.25
    rier
    -0.25
    CGRect
    -0.24
    iated
    -0.24
    Sig
    -0.24
    æĤĶ
    -0.24
    yen
    -0.24
    -reg
    -0.24
    éĩį
    -0.24
    POSITIVE LOGITS
    éĻ·åħ¥äºĨ
    0.29
    åĩĩ
    0.26
    ä¼ļè°Ī
    0.26
    (AF
    0.26
    ynes
    0.26
     bottoms
    0.26
    utters
    0.25
    presence
    0.23
    ä¸ŃåĽ½åĪ¶éĢł
    0.23
     royalties
    0.23
    Activations Density 0.007%

    No Known Activations