© 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. 62735
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    ç¿Į
    -0.09
     Gloss
    -0.09
    æ»
    -0.08
    antro
    -0.08
    ively
    -0.08
    urd
    -0.08
    çŃīéĥ¨éŨ
    -0.08
    å¿ĥçIJĨ
    -0.07
    åľ£è¯ŀ
    -0.07
     desp
    -0.07
    POSITIVE LOGITS
    以æĿ¥
    0.13
    以ä¾Ĩ
    0.10
    è¿Ħ
    0.10
    æĹ¶æľŁ
    0.10
    çĶ»åį·
    0.09
    太ä¹ħ
    0.09
    æĹ¶æľŁçļĦ
    0.09
    اÙĦØ·
    0.09
     اÙĦÙħاض
    0.09
    è¿ĩåİ»
    0.09
    Activations Density 0.146%

    No Known Activations