© 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. 17765
    Prev
    Next
    INDEX
    Explanations

    say "for or to"

    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
    requent
    -0.27
    quoise
    -0.27
    çļĦä¸Ģ
    -0.26
     aute
    -0.26
    ersed
    -0.24
    ainted
    -0.24
    åľ¨åĨħçļĦ
    -0.23
    ocked
    -0.23
    è¾¹
    -0.23
    åŃ¦ä¹ł
    -0.23
    POSITIVE LOGITS
     for
    0.40
    .for
    0.33
    for
    0.33
     not
    0.31
     For
    0.31
    å¯¹ä½ł
    0.29
    对äºİ
    0.29
    _for
    0.29
    	for
    0.28
    For
    0.28
    Activations Density 0.011%

    No Known Activations