© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
     nhân
    -0.30
     Nhân
    -0.29
    åĬŁè¯¾
    -0.27
    å·²äºİ
    -0.27
    æĺ¯ä»ĸ
    -0.26
    orges
    -0.25
    organ
    -0.25
    ç»Ħç»ĩå¼Ģå±ķ
    -0.25
     pole
    -0.25
    ipline
    -0.24
    POSITIVE LOGITS
    cba
    0.30
    flater
    0.28
    fleet
    0.26
    amba
    0.25
     rede
    0.25
    ITIONS
    0.24
    pread
    0.23
    çī¹åĪ«
    0.23
    matter
    0.23
    æ°ĶåĢĻåıĺåĮĸ
    0.23
    Activations Density 0.004%

    No Known Activations