© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97675
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ¨ä»½
    -0.38
    -0.33
     alot
    -0.32
     chinese
    -0.31
    éĿŀ常çļĦ
    -0.30
     Whilst
    -0.28
    æħ¢æħ¢çļĦ
    -0.28
    æ·±åĪ»çļĦ
    -0.28
    ä¸įåģľçļĦ
    -0.28
     profound
    -0.27
    POSITIVE LOGITS
    æĨİ
    0.30
    ([$
    0.26
    ε
    0.26
    -index
    0.25
    âĸ¶
    0.24
    åĽŀ头
    0.24
    æ°Ľ
    0.24
    æľ¬ä¹¦
    0.24
     dese
    0.24
    Python
    0.24
    Activations Density 0.005%

    No Known Activations