© 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. 57338
    Prev
    Next
    INDEX
    Explanations

    I,

    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
    éĤ£ä¸ĢåĪ»
    -0.11
    æĮģå¹³
    -0.09
    åij³éģĵ
    -0.09
    è¾ħ
    -0.08
    illo
    -0.08
     dau
    -0.08
    ater
    -0.08
    Ñĩем
    -0.08
    ä¸įçŁ¥ä¸įè§ī
    -0.08
    æĥ³èµ·æĿ¥
    -0.08
    POSITIVE LOGITS
    ize
    0.11
    çļĦè¯Ŀè¯Ń
    0.10
     Redistributions
    0.09
    é«ĺåľ°
    0.09
    家å±ħ
    0.09
    èĤ¯å®ļæĺ¯
    0.09
    è·¯è¿ĩ
    0.09
    ãĥ¥ãĥ¼
    0.08
    è¿ĩåħ³
    0.08
    æŀģ度
    0.08
    Activations Density 0.027%

    No Known Activations