© 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. 52564
    Prev
    Next
    INDEX
    Explanations

    catalog entries and divisions

    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
    å°ıé¾Ļ
    -0.08
    åºľ
    -0.08
    heel
    -0.08
    æ¹Ľ
    -0.08
    olution
    -0.08
    asco
    -0.08
    ysz
    -0.08
     tang
    -0.08
     trace
    -0.08
    fo
    -0.08
    POSITIVE LOGITS
    æĹºçĽĽ
    0.10
    åŃ£
    0.10
    ences
    0.09
    åħ»
    0.09
    rium
    0.09
    овÑĭй
    0.09
    æĶ¾å¿ĥ
    0.09
    иÑĢование
    0.08
    ä¸ĩåįĥ
    0.08
    ting
    0.08
    Activations Density 0.004%

    No Known Activations