© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3293
    Prev
    Next
    INDEX
    Explanations

    examples

    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
    arer
    -0.09
    åĵªåĦ¿
    -0.09
    çľĭä¼¼
    -0.09
    ä¸ĭæ²ī
    -0.09
    bull
    -0.08
    è¿ĺåĮħæĭ¬
    -0.08
    iscrim
    -0.08
     dare
    -0.08
    绳
    -0.08
    æį®è¯´
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.10
    ä¹Łå°±
    0.09
    éĻĮ
    0.09
    usercontent
    0.08
    гÑĢамм
    0.08
    åĨĻåŃĹ楼
    0.08
     Atkins
    0.08
    otten
    0.08
    å®ŀè·µä¸Ń
    0.08
     оÑĤкÑĢÑĭÑĤ
    0.08
    Activations Density 0.241%

    No Known Activations