© 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. 37617
    Prev
    Next
    INDEX
    Explanations

    air flow and circulation

    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
    骡
    -0.09
    éĶĤ
    -0.09
    åıijåħī
    -0.09
    æĹĦ
    -0.08
    Fake
    -0.08
    综åIJĪæĢ§
    -0.08
    å®ī稳
    -0.08
    è¿Ľå±ķæĥħåĨµ
    -0.08
    çĶ³æĬ¥
    -0.08
    éĺŁä¼į
    -0.08
    POSITIVE LOGITS
    é£İ
    0.17
    é£İåı£
    0.17
    é£İæľº
    0.17
     wind
    0.16
    åIJ¹
    0.16
     airflow
    0.15
    wind
    0.15
    éĢļé£İ
    0.14
     Winds
    0.14
     winds
    0.13
    Activations Density 0.097%

    No Known Activations