© 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. 51875
    Prev
    Next
    INDEX
    Explanations

    institute of technology and circuit

    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
    è·Ĺ
    -0.11
    è··
    -0.10
    icont
    -0.09
    lek
    -0.09
    æĤ¬
    -0.08
    ktop
    -0.08
    åī§éĻ¢
    -0.08
    monic
    -0.08
    åıĺæĢģ
    -0.08
    æIJı
    -0.08
    POSITIVE LOGITS
    çŁ³æ²¹åĮĸå·¥
    0.11
     engineer
    0.10
    è¿ĻåIJį
    0.10
    å·¥ç¨ĭå¸Ī
    0.09
    	engine
    0.09
    åĩ¤
    0.09
     ÑĩеÑĢ
    0.09
     nâ
    0.09
    åIJĮæĥħ
    0.09
    åģĪ
    0.09
    Activations Density 0.142%

    No Known Activations