© 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. 37146
    Prev
    Next
    INDEX
    Explanations

    changes to

    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
    ÑģÑĤвие
    -0.11
    /thumb
    -0.09
    virt
    -0.09
    ç§Ģ
    -0.09
     налиÑĩие
    -0.09
     اÙĦÙħزÙĬد
    -0.09
    æ¯ĵ
    -0.09
    INGS
    -0.08
    iams
    -0.08
    缶
    -0.08
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.13
    åĴĮå®ĮåĸĦ
    0.13
    çİ°æľīçļĦ
    0.12
    çİ°æľī
    0.11
     existing
    0.11
    åĩĨå¤ĩå·¥ä½ľ
    0.10
    设计æĸ¹æ¡Ī
    0.10
    åij¨åĽ´çļĦ
    0.10
    /mod
    0.10
    åİŁæľī
    0.10
    Activations Density 0.053%

    No Known Activations