© 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. 19946
    Prev
    Next
    INDEX
    Explanations

    using a, an, Python, malloc

    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
     Leigh
    -0.10
    Nil
    -0.08
    æī©
    -0.08
    upert
    -0.08
    æĪ³
    -0.08
    æĦ«
    -0.08
    ä»ĬçĶŁ
    -0.08
     Holden
    -0.08
    壯
    -0.08
    edException
    -0.08
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.10
    严èĤĥ
    0.10
    个人è§ĤçĤ¹
    0.09
    离
    0.09
    æ¡Ĥ
    0.09
    è¿·
    0.09
    çĤ¹å¤ļ
    0.09
    éĵ¶æ²³
    0.08
    анÑģ
    0.08
    igrate
    0.08
    Activations Density 0.002%

    No Known Activations