© 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. 30329
    Prev
    Next
    INDEX
    Explanations

    since time/years

    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¿Ļè¾ĪåŃIJ
    -0.11
    åĴĦ
    -0.09
    æĻ®æŁ¥
    -0.09
    ãĤ¢ãĥ³
    -0.09
    éĢŀ
    -0.09
    计éĩı
    -0.08
    ç»ĪçĶŁ
    -0.08
    ä¸Ģæīĭ
    -0.08
    åĤ¬
    -0.08
    æĢģ度
    -0.08
    POSITIVE LOGITS
    羣æŃ£
    0.10
    osa
    0.10
    åĨįåĪ°
    0.09
     sore
    0.09
    åĽŀåĪ°äºĨ
    0.09
    çĿ½
    0.09
    å®ŀè´¨æĢ§
    0.08
    æĥ³å¿µ
    0.08
     Kenn
    0.08
    羣æŃ£åģļåĪ°
    0.08
    Activations Density 0.049%

    No Known Activations