© 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. 7911
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    èµ·èįī
    -0.26
    详ç»Ĩä»ĭç»į
    -0.26
    aed
    -0.26
     lest
    -0.25
    çĶ³è¯·äºº
    -0.25
     Jame
    -0.25
    renderer
    -0.24
    æĶ¹
    -0.24
    æ¸ħåįķ
    -0.24
    window
    -0.24
    POSITIVE LOGITS
    ä¸ĵå±ŀ
    0.25
    è¡¥åħħ
    0.24
    uptime
    0.24
     uptime
    0.24
     multic
    0.24
    åĩºæ¼Ķ
    0.24
    åıįé¦Ī
    0.24
    马æĭī
    0.23
     postfix
    0.23
    é¢Ľ
    0.23
    Activations Density 0.005%

    No Known Activations