© 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. 129169
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     repost
    -0.28
     pairs
    -0.28
    ica
    -0.25
    .pair
    -0.25
    (inv
    -0.25
    iferay
    -0.24
    æ°´æĻ¶
    -0.24
    ('*',
    -0.24
     requ
    -0.24
    ossa
    -0.24
    POSITIVE LOGITS
    éħ·
    0.26
    ertest
    0.26
    åĪºæ¿Ģ
    0.25
     Yao
    0.24
     cas
    0.24
    æŁ¯
    0.24
    é¼ĵ
    0.24
    cores
    0.24
    atore
    0.24
    uÃŃ
    0.23
    Activations Density 12.686%

    No Known Activations