© 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. 20245
    Prev
    Next
    INDEX
    Explanations

    logic and integrated circuits

    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
    ä¸ĢæĬ¹
    -0.10
    åı£ä¸Ń
    -0.09
    丢äºĨ
    -0.09
    pest
    -0.09
    èŀį
    -0.09
    èĭİ
    -0.09
    大å®ĹåķĨåĵģ
    -0.09
    untime
    -0.08
    æĦı大
    -0.08
    çķļ
    -0.08
    POSITIVE LOGITS
    éĽªèĬ±
    0.10
    ä¼ı
    0.08
    NSS
    0.08
    çĤ¯
    0.08
    å¤įæŁ¥
    0.08
    éĥ¨ä»¶
    0.08
    æ¸ļ
    0.08
    éĶĹ
    0.08
    pla
    0.08
    ixel
    0.07
    Activations Density 0.204%

    No Known Activations