© 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. 20019
    Prev
    Next
    INDEX
    Explanations

    end 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
    lp
    -0.08
    æľīæĿĥ
    -0.08
    \Base
    -0.08
    åħĢ
    -0.08
    åľ°éģĵ
    -0.08
    æ°´å¹³
    -0.08
     sve
    -0.08
    rede
    -0.08
    -General
    -0.08
    izations
    -0.08
    POSITIVE LOGITS
    麻çĥ¦
    0.10
    ä¸Ģ个å°ı
    0.09
    赶ä¸Ĭ
    0.09
    æĪ®
    0.09
    äºĭåĦ¿
    0.08
    çĥ¦æģ¼
    0.08
    еÑĨ
    0.08
    éĥ¨åĪĨåĨħ容
    0.08
    åħĭ
    0.08
    ä¾Ŀæ³ķ
    0.08
    Activations Density 0.170%

    No Known Activations