© 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. 110967
    Prev
    Next
    INDEX
    Explanations

    cultures and languages

    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
     Annual
    -0.27
    riel
    -0.27
    é«ĺæķĪçļĦ
    -0.26
    agher
    -0.26
    ableView
    -0.26
    æį»
    -0.26
    å®īåħ¨éļIJæĤ£
    -0.25
    é«ĺæ¡£
    -0.24
    èIJĺ
    -0.24
    ardware
    -0.24
    POSITIVE LOGITS
    ä¼łç»ŁæĸĩåĮĸ
    0.27
    ãģ©ãĤĮ
    0.26
     prevailed
    0.26
    trace
    0.26
     roots
    0.25
    roots
    0.25
    éĢł
    0.25
    æīĵåĩ»
    0.24
    éĥ½è¯´
    0.24
    éŀĺ
    0.24
    Activations Density 0.006%

    No Known Activations