© 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. 52562
    Prev
    Next
    INDEX
    Explanations

    "you can see"

    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
    æĪijçŁ¥éģĵ
    -0.13
    è°ģçŁ¥éģĵ
    -0.12
    å·¡
    -0.10
    LAS
    -0.10
    æĪijä»¬çŁ¥éģĵ
    -0.10
    æĪijåıijçİ°
    -0.10
    ç»ıæŁ¥
    -0.10
    è¦ģçŁ¥éģĵ
    -0.10
    LS
    -0.09
    çļĦçľĭæ³ķ
    -0.09
    POSITIVE LOGITS
    ç´¯
    0.10
    à¹ģว
    0.09
    osal
    0.09
    å¤ļä¹Ī
    0.09
    æĺ¯å¤ļä¹Ī
    0.09
     stil
    0.09
    iner
    0.09
    bru
    0.08
    riters
    0.08
    erval
    0.08
    Activations Density 0.120%

    No Known Activations