© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8461
    Prev
    Next
    INDEX
    Explanations

    on top 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
    andel
    -0.10
    ä¸ĩåįĥ
    -0.09
    æĵĺ
    -0.09
    voir
    -0.09
    ialis
    -0.09
    æľ¬äºº
    -0.09
    çŃīæĥħåĨµ
    -0.09
    åħ¼
    -0.09
    åIJ¬è§ģ
    -0.09
    اÙħÙĬØ©
    -0.09
    POSITIVE LOGITS
    ä¹ĭä¸Ĭ
    0.11
     atop
    0.10
    ä¸Ģå±Ĥ
    0.09
    çĪª
    0.09
    åŁºç¡Ģä¸Ĭ
    0.08
    ä¹ħäºĨ
    0.08
     layer
    0.08
    ä¸Ģå¥Ĺ
    0.08
    çĦī
    0.08
    åŁºäºİ
    0.08
    Activations Density 0.087%

    No Known Activations