© 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. 48104
    Prev
    Next
    INDEX
    Explanations

    mentioning or referring

    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
    éĩijé¢Ŀ
    -0.10
    å¿ĥè¡Ģ
    -0.09
    enia
    -0.09
     stil
    -0.09
    ä¸įä¸Ģæł·çļĦ
    -0.09
    åIJĦè¡Į
    -0.09
    OOT
    -0.09
    /helpers
    -0.08
    ä»»ä½ķä¸Ģ个
    -0.08
    ä¸ŃåİŁ
    -0.08
    POSITIVE LOGITS
    说è¿ĩ
    0.17
    æıIJåıĬ
    0.16
     mentioned
    0.16
     mention
    0.15
    æıIJåĪ°
    0.15
    åīįæīĢ
    0.14
    mentioned
    0.14
    åīįéĿ¢
    0.14
     earlier
    0.14
    说åĪ°
    0.14
    Activations Density 0.055%

    No Known Activations