© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 33736
    Prev
    Next
    INDEX
    Explanations

    companies and institutions

    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
    çζ
    -0.10
    个åĪ«
    -0.09
    æĸ°éĻĪ代谢
    -0.09
    æĤ£çĹħ
    -0.09
    äºĭæķħåıijçĶŁ
    -0.08
    å¼łè´´
    -0.08
    è¿Ľè´§
    -0.08
    ä¸įç¡®å®ļ
    -0.08
    iore
    -0.08
    æĦŁåĨĴ
    -0.08
    POSITIVE LOGITS
    çłĶç©¶éĻ¢
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    çī¹èī²çļĦ
    0.10
    å¼Ģåıij
    0.10
    ä¹Łæĺ¯éĿŀ常
    0.09
    èµĦè´¨
    0.09
    产ä¸ļåĮĸ
    0.09
    ä¸ĵä¸ļåĮĸ
    0.09
    èµ°åĩºåİ»
    0.09
    ä¿¡æģ¯åĮĸ
    0.09
    Activations Density 0.317%

    No Known Activations