© 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. 21907
    Prev
    Next
    INDEX
    Explanations

    israel

    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
    é»Ķ
    -0.09
    è¹ĩ
    -0.09
    èĬ¡
    -0.09
    çĶ°åĽŃ
    -0.09
    ç´§
    -0.08
     Curt
    -0.08
    åĮĸå·¥
    -0.08
    æĪªæŃ¢
    -0.08
    侵害
    -0.08
    SKI
    -0.08
    POSITIVE LOGITS
    åľ£åľ°
    0.11
    å´İ
    0.09
    izr
    0.08
    обоÑĢ
    0.08
    çIJ¦
    0.08
    æĵ¦æĭŃ
    0.08
    稽
    0.08
    äºī夺
    0.08
    åı¤åŁİ
    0.08
    -region
    0.08
    Activations Density 0.033%

    No Known Activations