© 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. 108537
    Prev
    Next
    INDEX
    Explanations

    vacation

    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
     Achilles
    -0.30
     breadcrumbs
    -0.28
    ç¿®
    -0.27
    zend
    -0.25
    "Now
    -0.25
     tilt
    -0.24
    åĩ¶
    -0.24
    til
    -0.24
    tip
    -0.24
     shouts
    -0.23
    POSITIVE LOGITS
    jej
    0.30
    å½ĵæĪij
    0.28
    orian
    0.27
    rocessing
    0.26
    åıĪæĺ¯
    0.26
    ëł¹
    0.26
    AAF
    0.26
    让æĪij
    0.25
    ä¸Ģå¹ħ
    0.25
     Downs
    0.25
    Activations Density 9.863%

    No Known Activations