© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19824
    Prev
    Next
    INDEX
    Explanations

    months 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
    笼
    -0.10
    æ¯ıéļĶ
    -0.10
    .va
    -0.09
    çļĦ人çĶŁ
    -0.09
    çį¾
    -0.09
    âĩ¦
    -0.09
    ç¿¡
    -0.09
    доб
    -0.09
    ç²Ĺ
    -0.09
    PropertyParams
    -0.09
    POSITIVE LOGITS
     ìŀ¥
    0.08
    éĨĴæĿ¥
    0.08
    å¤Ħäºİ
    0.08
    eya
    0.08
    psc
    0.08
     diá»ħn
    0.08
    my
    0.08
     Cres
    0.08
    hs
    0.08
    å°±æĺ¯è¿Ļæł·
    0.08
    Activations Density 0.030%

    No Known Activations