© 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. 7574
    Prev
    Next
    INDEX
    Explanations

    up / on / out

    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
    åĽŀæĬ¥
    -0.08
    emic
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    å®ŀå®ŀåľ¨åľ¨
    -0.08
    åĢºåĪ¸
    -0.08
    çģ«ç®Ń
    -0.08
    æłĩ
    -0.08
    å¾ĪæŃ£å¸¸
    -0.08
    åIJĮæł·çļĦ
    -0.08
    ä½łæĢİä¹Ī
    -0.08
    POSITIVE LOGITS
    åIJĮåѦ们
    0.09
    onders
    0.09
    çIJīçĴĥ
    0.09
    ç¨Ĺ
    0.08
    éļħ
    0.08
    å¿ĥä¸Ń
    0.08
     shaved
    0.08
    åĪĩåħ¥
    0.08
     Hod
    0.08
    夤
    0.08
    Activations Density 0.060%

    No Known Activations