© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48429
    Prev
    Next
    INDEX
    Explanations

    do not edit or avoid

    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
     lá»Ļ
    -0.09
    èĢĦ
    -0.08
    温åĴĮ
    -0.08
    osci
    -0.08
    çģ¯ç¬¼
    -0.08
    亥
    -0.08
    nte
    -0.08
     polled
    -0.08
    鼷éľĨ
    -0.08
    ÑĩÑĥ
    -0.08
    POSITIVE LOGITS
    çĽ²çĽ®
    0.12
    èĩªè¡Į
    0.12
    æľªç»ı
    0.11
    æĵħèĩª
    0.11
    è´¸
    0.10
    延误
    0.09
    å²Ĺä½į
    0.09
    æłı缮
    0.09
    ä¸įç»ı
    0.09
    çľĭä¸įæĩĤ
    0.09
    Activations Density 0.054%

    No Known Activations