© 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. 32-TRANSCODER-HP
    7. 44247
    Prev
    Next
    INDEX
    Explanations

    live

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Record
    -0.30
    è®°å½ķ
    -0.29
    fix
    -0.28
    record
    -0.28
     record
    -0.27
    Record
    -0.27
    opt
    -0.26
    -record
    -0.26
    å±ı
    -0.25
    纪å½ķ
    -0.25
    POSITIVE LOGITS
    è¿Ļ个ä¸ĸçķĮ
    0.28
     Mattis
    0.27
    ä¸įè¿ľ
    0.27
     foll
    0.25
    FetchRequest
    0.24
     worlds
    0.24
    è·¨çķĮ
    0.24
    ä¸Ģ个éĩįè¦ģ
    0.24
    çĶŁäº§åĴĮ
    0.23
    -legged
    0.23
    Activations Density 0.010%

    No Known Activations