© 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. 36250
    Prev
    Next
    INDEX
    Explanations

    required fields or copyright notices

    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
    åĪ¸
    -0.09
    æ¸ħæ·¡
    -0.09
    åIJİåĨį
    -0.09
    第ä¸Ģä½į
    -0.09
     ведÑĮ
    -0.09
    é¦ĸä½į
    -0.09
    ä½ĵèĤ²é¦Ĩ
    -0.09
     ÐĴедÑĮ
    -0.08
    人èĦī
    -0.08
    ä¹IJåĽŃ
    -0.08
    POSITIVE LOGITS
     outf
    0.09
    ä¼¼
    0.09
    æģº
    0.08
    亵
    0.08
    POL
    0.08
    驯
    0.08
    acci
    0.08
     Noble
    0.08
    DMIN
    0.08
    ç»
    0.08
    Activations Density 0.043%

    No Known Activations