© 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. 58363
    Prev
    Next
    INDEX
    Explanations

    there

    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
    of
    -0.28
    çļĦå°±æĺ¯
    -0.27
    abouts
    -0.27
    æĺ¯å¯¹
    -0.27
     besides
    -0.27
    å¾Ĺ天
    -0.27
    çļĦæĺ¯
    -0.27
    omat
    -0.26
     beside
    -0.25
    SD
    -0.25
    POSITIVE LOGITS
    there
    0.51
     there
    0.46
     THERE
    0.37
    è¿ĻéĩĮæľī
    0.37
     There
    0.36
    åľ¨éĤ£éĩĮ
    0.36
    There
    0.34
    éĤ£éĩĮ
    0.34
    è¿ĻéĩĮ
    0.33
     ÙĩÙĨاÙĥ
    0.31
    Activations Density 0.885%

    No Known Activations