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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6382
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lag
    -0.25
    (where
    -0.24
    åľºéĿ¢
    -0.23
    éĩijé¢Ŀ
    -0.23
    ität
    -0.23
    lags
    -0.23
    趸
    -0.23
    æݾ
    -0.22
    ária
    -0.22
     spectacle
    -0.22
    POSITIVE LOGITS
     sure
    0.29
    è¯Ŀ
    0.25
    enia
    0.25
     ultimate
    0.24
     creeping
    0.23
     earth
    0.23
    compress
    0.23
    åĪ°æĿ¥
    0.23
     real
    0.22
    pta
    0.22
    Activations Density 0.525%

    No Known Activations