© 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. 9536
    Prev
    Next
    INDEX
    Explanations

    increasing number or incidence

    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
    æĿ¡ä»¶ä¸ĭ
    -0.09
    awai
    -0.08
    eder
    -0.08
    eman
    -0.08
     Transport
    -0.08
    éĢļåħ³
    -0.08
    æĺ¯å¯¹
    -0.08
    çĬ¶æĢģä¸ĭ
    -0.08
    onis
    -0.08
    _neighbor
    -0.08
    POSITIVE LOGITS
    åıĺå¾ĹæĽ´åĬł
    0.17
    åıĺå¾Ĺ
    0.17
    åıĺå¾ĹæĽ´
    0.13
    è®Ĭå¾Ĺ
    0.13
    ãģĮå¢ĹãģĪ
    0.13
    éļıçĿĢ
    0.12
    çĶŁæ´»æ°´å¹³
    0.12
    æĦĪåıij
    0.12
    åıĺäºĨ
    0.12
    çļĦå¢ŀéķ¿
    0.12
    Activations Density 0.339%

    No Known Activations