© 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. 108652
    Prev
    Next
    INDEX
    Explanations

    that

    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
    说æĪij
    -0.26
    åijĪ
    -0.26
    奢
    -0.25
    åħľ
    -0.25
    arius
    -0.24
    æĶ¶åħ¥
    -0.24
    æİĬ
    -0.24
    çļĦåİĭåĬĽ
    -0.24
    éĵ®
    -0.24
     доÑħод
    -0.23
    POSITIVE LOGITS
    èħł
    0.29
    ä¸ĢæľŁ
    0.26
    .Cursors
    0.26
     sublic
    0.26
    apes
    0.26
    traits
    0.25
    ;break
    0.25
    leases
    0.25
    âĪ
    0.25
     chaining
    0.25
    Activations Density 12.183%

    No Known Activations