© 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. 21122
    Prev
    Next
    INDEX
    Explanations

    change and adaptation

    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
    åĪĨ级
    -0.09
    è¾ħ
    -0.09
    æĬł
    -0.09
    æĺŁçº§
    -0.09
    пон
    -0.08
    èĥ½å¾ĹåĪ°
    -0.08
    è¾¾æłĩ
    -0.08
    _ACL
    -0.08
    让åŃ©åŃIJ
    -0.08
    enti
    -0.08
    POSITIVE LOGITS
    éĢĤåºĶ
    0.16
    åıĺéĿ©
    0.16
    åıĺåĮĸ
    0.16
     change
    0.13
     Change
    0.13
     changes
    0.13
    çļĦåıĺåĮĸ
    0.13
    åıĺå¹»
    0.12
    顺åºĶ
    0.12
    åıĺè¿ģ
    0.12
    Activations Density 0.099%

    No Known Activations