© 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. 131226
    Prev
    Next
    INDEX
    Explanations

    Alphanumeric code/URLs

    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
    олод
    -0.28
    çķĻä¸ĭ
    -0.26
    adier
    -0.25
    idata
    -0.25
    vier
    -0.24
    åĿĢ
    -0.24
    anker
    -0.24
     sadd
    -0.24
    horn
    -0.24
    setLayout
    -0.24
    POSITIVE LOGITS
    å°ıç¼ĸ
    0.27
    Cent
    0.27
    etus
    0.25
    èµ·åĪĿ
    0.25
    æĿĤ
    0.25
    çī¹
    0.25
    åĢĴ
    0.25
    æĪij们çļĦ
    0.25
    åįģäºĮ
    0.25
    0
    0.24
    Activations Density 0.068%

    No Known Activations