© 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. 31-TRANSCODER-HP
    7. 17869
    Prev
    Next
    INDEX
    Explanations

    words related to "sh"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Ned
    -0.26
    æ´¥
    -0.26
    éľŃ
    -0.25
    setContent
    -0.25
     FU
    -0.24
     TEMPLATE
    -0.24
    redi
    -0.24
    ä¸ĩäºĭ
    -0.24
    æķĻèĤ²èµĦæºIJ
    -0.24
    Classification
    -0.24
    POSITIVE LOGITS
    -sh
    0.72
     Sh
    0.56
    sh
    0.56
    _sh
    0.54
    	sh
    0.53
    Sh
    0.52
     SH
    0.51
     sh
    0.51
     sha
    0.50
    -Sh
    0.50
    Activations Density 41.069%

    No Known Activations