© 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. 33-TRANSCODER-HP
    7. 54672
    Prev
    Next
    INDEX
    Explanations

    economics and studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¾Ĭ
    -0.26
    大èħ¿
    -0.26
    sti
    -0.26
    èĤļåŃIJ
    -0.25
    Accessor
    -0.25
     pals
    -0.25
    æį£
    -0.24
     TableRow
    -0.24
    çĮ¥
    -0.24
    ä¹ĭä¸Ģ
    -0.23
    POSITIVE LOGITS
     dem
    0.29
     population
    0.29
    æĶ¸
    0.28
     specification
    0.28
    çĩķ
    0.27
    egov
    0.26
    æ¹ĸåĮº
    0.26
    [value
    0.25
    âĨij
    0.25
     currentPosition
    0.25
    Activations Density 0.006%

    No Known Activations