© 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. 6621
    Prev
    Next
    INDEX
    Explanations

    Russian names and technical terms

    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
    çªĿ
    -0.11
    éģĹçķĻ
    -0.11
    è¡°
    -0.10
    æĹłçŁ¥
    -0.09
    á»ģn
    -0.09
    ington
    -0.09
    ç³Ĭæ¶Ĥ
    -0.09
    aris
    -0.09
    berry
    -0.09
    akov
    -0.08
    POSITIVE LOGITS
    dan
    0.10
    Assembler
    0.09
    æħĪ
    0.09
    å§ĭç»Īä¿ĿæĮģ
    0.08
    alytics
    0.08
     crews
    0.08
    æ²IJ
    0.08
    æ°ijçĶŁ
    0.08
    ัà¸ļ
    0.08
    (lst
    0.08
    Activations Density 0.237%

    No Known Activations