© 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. 8018
    Prev
    Next
    INDEX
    Explanations

    time for

    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
    æģ£
    -0.10
    sr
    -0.08
     Fol
    -0.08
     اÙĦØ«ÙĦاث
    -0.08
    æľīåĬ©
    -0.08
    è·Į
    -0.08
    å§ľ
    -0.08
    æĹĭ
    -0.08
     br
    -0.08
     sadd
    -0.08
    POSITIVE LOGITS
    èIJ¥
    0.10
    æĬ¥éĢģ
    0.09
    èIJ¥åķĨ
    0.09
    éĻį临
    0.09
    ä¸įéĢĤåIJĪ
    0.09
    çĩŁ
    0.09
    ä¸Ńå¼ı
    0.09
     ká»ĥ
    0.09
    à¹ģห
    0.08
    asher
    0.08
    Activations Density 0.022%

    No Known Activations