© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8847
    Prev
    Next
    INDEX
    Explanations

    Ferris, Crush

    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
    .gravity
    -0.09
    __.__
    -0.09
    äºļåĨĽ
    -0.09
    æ¶Ī
    -0.08
    à¸ĺรรม
    -0.08
    ummings
    -0.08
    åĽ½æ°ij
    -0.08
    uib
    -0.08
    ubits
    -0.08
     Lav
    -0.08
    POSITIVE LOGITS
    rait
    0.09
    å¤ļå°ijéĴ±
    0.09
    è¿Ļ两
    0.09
    åºł
    0.09
    污水å¤ĦçIJĨ
    0.08
    è´¨éĩıåĴĮ
    0.08
    è°ģéĥ½
    0.08
    æģª
    0.08
    dere
    0.08
    ç»Ļèĩªå·±
    0.08
    Activations Density 0.001%

    No Known Activations