© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21756
    Prev
    Next
    INDEX
    Explanations

    Tissa, Colombo, Buddhism, MySQL, random, modified

    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
    yre
    -0.09
    çļĩå¸Ŀ
    -0.09
    аÑĤа
    -0.09
    åŁ½
    -0.08
    é¢ĦçķĻ
    -0.08
    管çIJĨç³»ç»Ł
    -0.08
    олÑĮз
    -0.08
    éŀij
    -0.08
    è±¹
    -0.08
    èĪįå¾Ĺ
    -0.08
    POSITIVE LOGITS
     ëĶ°
    0.10
    è´£
    0.10
    DebugEnabled
    0.09
    æijĬ
    0.09
    è¸ı
    0.09
    碾
    0.09
     вне
    0.09
    æ³ķå¸Ī
    0.09
     Buddh
    0.09
    undef
    0.09
    Activations Density 0.043%

    No Known Activations