© 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. 19-TRANSCODER-HP
    7. 8437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åijĬ
    -0.27
     acess
    -0.25
    æĸľ
    -0.24
    人äºĭ
    -0.24
    è§ģ解
    -0.23
    ÙĨسÙĬ
    -0.23
    icle
    -0.23
    æĶ¾å¤§
    -0.23
    imenti
    -0.23
    imento
    -0.23
    POSITIVE LOGITS
    unched
    0.34
    æµĴ
    0.27
    æľĢ为
    0.27
    éĩİå¤ĸ
    0.25
    æ¼ĵ
    0.25
    _EMIT
    0.24
    æľĢæĸ°çļĦ
    0.24
    azzi
    0.24
    upal
    0.23
    ikon
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.