© 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. 9688
    Prev
    Next
    INDEX
    Explanations

    variations of the word "form"

    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
    ooke
    -0.28
     replacement
    -0.27
    å¥Ĺ
    -0.26
    inia
    -0.26
    istik
    -0.25
     substitution
    -0.25
     NUM
    -0.25
    æĥħ趣
    -0.25
    marked
    -0.25
    ogra
    -0.25
    POSITIVE LOGITS
    å½¢å¼ı
    0.54
    çļĦå½¢å¼ı
    0.52
     forms
    0.47
     form
    0.42
    çŃīå½¢å¼ı
    0.41
     ÑĦоÑĢма
    0.40
     forma
    0.38
     ÑĦоÑĢме
    0.37
     Forms
    0.36
     formas
    0.35
    Activations Density 0.000%

    No Known Activations