© 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. 20-TRANSCODER-HP
    7. 108619
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¡Ĩæŀ¶
    -0.28
    æĢ»éĩı
    -0.27
    ropp
    -0.27
    imizer
    -0.26
    设
    -0.25
    ãĥĬãĤ¤
    -0.25
    (sw
    -0.25
    omatic
    -0.25
    Else
    -0.24
     tamp
    -0.24
    POSITIVE LOGITS
     voice
    0.26
    igi
    0.24
    èĬĤ
    0.24
     tops
    0.24
     requiring
    0.24
    -rise
    0.24
    raphics
    0.23
    ì¹ĺ
    0.23
    ìłķ
    0.23
    æ¼Ķåijĺ
    0.23
    Activations Density 21.098%

    No Known Activations