© 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. 36039
    Prev
    Next
    INDEX
    Explanations

    same, similar, generic, homogeneous

    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
    ä¼´
    -0.09
    樵
    -0.09
    æŃª
    -0.09
    orra
    -0.09
    å¿Ĺ强
    -0.08
    åī§ä¸Ń
    -0.08
    åī§
    -0.08
    çļĩåĨł
    -0.08
    æĸľ
    -0.08
    æŀ
    -0.08
    POSITIVE LOGITS
    generic
    0.14
    çĽ¸ä¼¼
    0.14
     generic
    0.13
     identical
    0.12
    éĢļçĶ¨
    0.12
     Generic
    0.12
    -generic
    0.12
    缸åIJĮçļĦ
    0.12
    Generic
    0.11
    ä¸Ģæł·çļĦ
    0.11
    Activations Density 0.067%

    No Known Activations