© 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. 17951
    Prev
    Next
    INDEX
    Explanations

    MIT, Fellow, Navigation, Breast, Xenografts

    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
    å±¥
    -0.11
     nerve
    -0.10
    æ»ĭåħ»
    -0.10
     PRIV
    -0.10
    å¨ģæħij
    -0.09
    éĻIJéĩı
    -0.09
    ä¸įè´Ł
    -0.09
    é£ŀæī¬
    -0.09
    姿
    -0.09
    éĸ±
    -0.09
    POSITIVE LOGITS
    èĩªä¸»åĪĽæĸ°
    0.09
    èģªæĺİ
    0.09
    çł´è§£
    0.09
    åѦä¼ļ
    0.09
    寿
    0.08
    æ¸ħæĻ°
    0.08
    人æĢ§
    0.08
    壽
    0.08
     влад
    0.08
    寿åij½
    0.08
    Activations Density 0.096%

    No Known Activations