© 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. 20-TRANSCODER-HP
    7. 141129
    Prev
    Next
    INDEX
    Explanations

    teaching

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĢ¾
    -0.28
    SELL
    -0.25
    æĪij们ä¼ļ
    -0.24
     Howell
    -0.24
    ymology
    -0.24
    OLLOW
    -0.24
    /AP
    -0.23
    abı
    -0.23
    ASI
    -0.23
    zym
    -0.23
    POSITIVE LOGITS
    æ¶Ŀ
    0.25
    ises
    0.24
    ivet
    0.24
    æİĮ
    0.24
    ä¸ĸçķĮçļĦ
    0.24
    转移åĪ°
    0.24
    -option
    0.23
    Options
    0.23
     mo
    0.23
    chaft
    0.23
    Activations Density 20.244%

    No Known Activations