© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6746
    Prev
    Next
    INDEX
    Explanations

    per

    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
    |M
    -0.29
    è§ģéĿ¢
    -0.28
    antee
    -0.28
    åĪĩãĤĮ
    -0.27
    åħįçĸ«åĬĽ
    -0.25
     nose
    -0.25
    é¼»
    -0.25
     MUT
    -0.25
    æľīæķĪæĢ§
    -0.25
    atedRoute
    -0.25
    POSITIVE LOGITS
    ÑĮÑı
    0.27
    .Pattern
    0.27
     retr
    0.26
    桨
    0.25
    ç´ĭ
    0.25
     murm
    0.24
    xBF
    0.24
     OPC
    0.24
    大å¤ļæķ°
    0.24
    æĮĩ
    0.24
    Activations Density 0.007%

    No Known Activations