© 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. 27-TRANSCODER-HP
    7. 58360
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pand
    -0.29
    æľĽ
    -0.29
    ä¼ı
    -0.28
    rdf
    -0.28
    lug
    -0.26
     speak
    -0.25
    è¯Ń
    -0.25
    åľ¨æľªæĿ¥
    -0.25
    æŀģåĬĽ
    -0.24
     anthrop
    -0.24
    POSITIVE LOGITS
    vie
    0.27
    çķ¸å½¢
    0.26
    æĹĹ
    0.26
    tmpl
    0.26
    contest
    0.25
    task
    0.24
    èĤĮèĤ¤
    0.24
    æ¯ĶåĪĨ
    0.24
    åİŁåĽł
    0.24
     Narrow
    0.23
    Activations Density 0.010%

    No Known Activations