© 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. 8320
    Prev
    Next
    INDEX
    Explanations

    apartment descriptions

    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
    ä¹¡åľŁ
    -0.11
    ÑĪа
    -0.10
    宵
    -0.09
    èļ±
    -0.09
    ç«ŀäºī
    -0.09
    iesel
    -0.09
    TECT
    -0.09
    èļĮ
    -0.09
    Hat
    -0.09
    Į¨
    -0.09
    POSITIVE LOGITS
     اÙĦÙħص
    0.09
    åįķåħĥ
    0.09
    éĢı
    0.09
     ÐľÐ¾Ñģква
    0.08
    履约
    0.08
     ÐľÐ¾ÑģквÑĭ
    0.08
    åī¥
    0.08
    éĴIJ
    0.08
    à¹Ĥà¸ģ
    0.08
    /topics
    0.08
    Activations Density 0.072%

    No Known Activations