© 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. 4310
    Prev
    Next
    INDEX
    Explanations

    purported claims

    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
    _stub
    -0.11
    è¢ĭåŃIJ
    -0.10
    ç°Į
    -0.10
    æīİå®ŀ
    -0.09
    åŃ³
    -0.09
    åķ»
    -0.09
    ä¼ĺç§ĢçļĦ
    -0.09
    éĿ¢è²Į
    -0.09
    ä¸Ģ缴éĥ½æĺ¯
    -0.09
    模èĮĥ
    -0.09
    POSITIVE LOGITS
    æīĢè°ĵ
    0.16
    æīĢè°ĵçļĦ
    0.15
    声称
    0.14
    æīĢè¬Ĥ
    0.12
    宣称
    0.12
     purported
    0.12
    èĩªç§°
    0.10
     supposed
    0.10
    Claims
    0.10
     allegedly
    0.09
    Activations Density 0.147%

    No Known Activations