© 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. 24-TRANSCODER-HP
    7. 149529
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦè®°å¿Ĩ
    -0.28
    é£ŀæī¬
    -0.27
    ä¸Ģä¼ļåĦ¿
    -0.26
    æľ¬æĬ¥è®¯
    -0.25
    nodoc
    -0.25
    åħ¥åºĵ
    -0.25
     Instant
    -0.25
    ãģķãģĪ
    -0.25
    åıªè§ģ
    -0.24
    artisan
    -0.24
    POSITIVE LOGITS
    ison
    0.30
    大
    0.29
    ded
    0.27
    æīĵ
    0.27
    ision
    0.27
    äº
    0.26
    代
    0.26
     æī
    0.25
    家
    0.25
     cheek
    0.25
    Activations Density 0.272%

    No Known Activations