© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    can't figure out

    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
    èĥ½å¤Ł
    -0.12
    ä¸įèĩ³äºİ
    -0.12
    èĥ½å¤Łåľ¨
    -0.11
     pouvoir
    -0.11
     poder
    -0.10
    èĥ½åľ¨
    -0.10
    èĥ½å¤ł
    -0.10
    åı¯ä»¥ä»İ
    -0.09
    åı¯è¾¾
    -0.09
    uite
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.15
     anymore
    0.14
     سÙĪÙī
    0.12
    ä¸ĩä¸Ģ
    0.12
    ä¹ŁæĹłæ³ķ
    0.12
     afford
    0.12
    anything
    0.11
    ä¹Łä¸įæĥ³
    0.11
    ä¹Łä¸įèĥ½
    0.11
    ä»»ä½ķ人
    0.11
    Activations Density 0.205%

    No Known Activations