© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53952
    Prev
    Next
    INDEX
    Explanations

    complex word strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľĽ
    -0.09
    éļ½
    -0.09
    _rb
    -0.09
    楫
    -0.09
    åľ¨å¤ĸ
    -0.08
    棹
    -0.08
    åģļ梦
    -0.08
    æĬĬæĮģ
    -0.08
    å¾Ĺå¤ļ
    -0.08
    å±į
    -0.08
    POSITIVE LOGITS
    åħīçݯ
    0.11
    ä¸Ģéģĵ
    0.10
    ä¸Ģéĺµ
    0.10
    éĩijèī²
    0.10
    æĻ°
    0.10
    еÑĢÑĭ
    0.09
    .yy
    0.09
    åħīèĬĴ
    0.08
    CHK
    0.08
    æ»ĭ
    0.08
    Activations Density 0.031%

    No Known Activations