© 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. 38440
    Prev
    Next
    INDEX
    Explanations

    List of

    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
    æĪĺæľ¯
    -0.09
    np
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    åĴİ
    -0.09
     ÙĬعد
    -0.08
    lopedia
    -0.08
    ä½Ĺ
    -0.08
    енно
    -0.08
    çĮ·
    -0.08
    éªĦ
    -0.08
    POSITIVE LOGITS
    åħ®
    0.09
    å°º
    0.08
    èµ·çĤ¹
    0.08
    lijah
    0.08
    ains
    0.08
     Suk
    0.08
    bery
    0.08
     networking
    0.08
     suk
    0.08
     Peel
    0.08
    Activations Density 0.068%

    No Known Activations