© 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. 36626
    Prev
    Next
    INDEX
    Explanations

    anyone, else

    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
    ran
    -0.10
    æŁIJç§į
    -0.10
    ä»İäºĭ
    -0.10
    ç¥ŀ
    -0.09
    åı¦ä¸Ģç§į
    -0.09
    æ¯ıä½į
    -0.09
    趣
    -0.08
     pan
    -0.08
    è¿Ļæī¹
    -0.08
     Glas
    -0.08
    POSITIVE LOGITS
     else
    0.17
    else
    0.12
    	else
    0.11
    _else
    0.11
    ELSE
    0.10
     ELSE
    0.09
    æľĽ
    0.09
    çĮ·
    0.09
    Else
    0.09
    ä¹ĭæīĢ
    0.09
    Activations Density 0.053%

    No Known Activations