© 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. 52658
    Prev
    Next
    INDEX
    Explanations

    which to use or take

    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
    ç¾¼
    -0.09
    ÙĪÙħØ©
    -0.09
    å½¢
    -0.08
     ниÑĩ
    -0.08
    ä¸Ńæĸ°
    -0.08
    STIT
    -0.08
    æĥ³åĥı
    -0.08
    ãĤ¦ãĤ©
    -0.08
    IDES
    -0.08
    åĭĻ
    -0.08
    POSITIVE LOGITS
     Caf
    0.10
     expect
    0.10
    çĪ¸
    0.10
    èĦIJ
    0.10
    çĪ¸çĪ¸
    0.10
    ä¸Ģæīĭ
    0.10
    ä¸ĭæīĭ
    0.09
    æĮijåīĶ
    0.09
    ä¸ĢåĪĻ
    0.09
     Zuk
    0.09
    Activations Density 0.045%

    No Known Activations